├── LICENSE ├── README.md ├── assets └── framework.png ├── data └── .DS_Store ├── eval_GQA.py ├── eval_VQA.py ├── eval_prompts.py ├── eval_reward.py ├── eval_temporal_grounding.py ├── eval_temporal_grounding_multi.py ├── inference_vllm_multiturn_number.py ├── inference_vllm_origin.py ├── inference_vllm_origin_number.py ├── setup.sh ├── train_stage_1_sft.sh ├── train_stage_2_dgrpo.sh ├── train_stage_3_sft.sh ├── train_stage_4_dgrpo.sh └── verl ├── .DS_Store ├── .pre-commit-config.yaml ├── .readthedocs.yaml ├── BytedDockerfile ├── LICENSE ├── Notice.txt ├── README.md ├── docker ├── Apptainerfile.rocm ├── Dockerfile.awsefa ├── Dockerfile.ngc.vllm ├── Dockerfile.ngc.vllm0.8 ├── Dockerfile.ngc.vllm0.8.sagemaker ├── Dockerfile.rocm ├── Dockerfile.sglang ├── Dockerfile.vemlp.vllm.te ├── Dockerfile.vllm.sglang.megatron └── Dockerfile.vllm.sglang.megatron.deepseek ├── docs ├── Makefile ├── README.md ├── README_vllm0.7.md ├── README_vllm0.8.md ├── _static │ ├── js │ │ └── runllm-widget.js │ └── logo.png ├── advance │ ├── checkpoint.rst │ ├── dpo_extension.rst │ ├── fsdp_extension.rst │ ├── megatron_extension.rst │ ├── placement.rst │ ├── ppo_lora.rst │ └── rope.rst ├── algo │ ├── baseline.md │ ├── dapo.md │ ├── grpo.md │ ├── opo.md │ ├── ppo.md │ ├── spin.md │ └── sppo.md ├── amd_tutorial │ ├── amd_build_dockerfile_page.rst │ └── amd_vllm_page.rst ├── api │ ├── data.rst │ ├── single_controller.rst │ ├── trainer.rst │ └── utils.rst ├── ascend_tutorial │ └── ascend_quick_start.rst ├── conf.py ├── examples │ ├── config.rst │ ├── gsm8k_example.rst │ ├── multi_modal_example.rst │ ├── ppo_code_architecture.rst │ └── sandbox_fusion_example.rst ├── faq │ └── faq.rst ├── hybrid_flow.rst ├── index.rst ├── perf │ ├── device_tuning.rst │ ├── dpsk.md │ └── perf_tuning.rst ├── preparation │ ├── prepare_data.rst │ └── reward_function.rst ├── requirements-docs.txt ├── sglang_multiturn │ ├── multiturn.rst │ ├── sandbox_fusion.rst │ └── search_tool_example.rst ├── single_controller.rst ├── start │ ├── install.rst │ ├── multinode.rst │ ├── quickstart.rst │ └── ray_debug_tutorial.rst └── workers │ ├── fsdp_workers.rst │ ├── megatron_workers.rst │ ├── ray_trainer.rst │ └── sglang_worker.rst ├── examples ├── data_preprocess │ ├── aime2024_multiturn_w_tool.py │ ├── dapo_multiturn_w_tool.py │ ├── full_hh_rlhf.py │ ├── geo3k.py │ ├── gsm8k.py │ ├── gsm8k_multiturn_w_tool.py │ ├── hellaswag.py │ ├── math_dataset.py │ ├── multiturn.py │ └── preprocess_search_r1_dataset.py ├── generation │ ├── run_deepseek7b_mutli_node.sh │ └── run_deepseek_v2_lite_math.sh ├── grpo_trainer │ ├── README.md │ ├── run_deepseek671b_math_megatron.sh │ ├── run_deepseek7b_llm.sh │ ├── run_deepseek7b_llm_math.sh │ ├── run_deepseek7b_llm_math_megatron.sh │ ├── run_deepseek7b_llm_seq_balance.sh │ ├── run_moonlight16b_math_megatron.sh │ ├── run_qwen2-7b.sh │ ├── run_qwen2-7b_math.sh │ ├── run_qwen2-7b_math_megatron.sh │ ├── run_qwen2-7b_seq_balance.sh │ ├── run_qwen2-7b_seq_balance_math_megatron.sh │ ├── run_qwen2-7b_sgl_megatron.sh │ ├── run_qwen2_5-3b_gsm8k_grpo_lora.sh │ ├── run_qwen2_5-7b_math_megatron_diff_tp.sh │ ├── run_qwen2_5_vl-7b-megatron.sh │ ├── run_qwen2_5_vl-7b.sh │ ├── run_qwen3-236b_megatron.sh │ ├── run_qwen3-8b.sh │ └── run_qwen3moe-30b_megatron.sh ├── ppo_trainer │ ├── README.md │ ├── run_deepseek7b_llm.sh │ ├── run_deepseek7b_llm_modelscope.sh │ ├── run_deepseek7b_llm_pfppo.sh │ ├── run_deepseek7b_llm_sandbox_fusion.sh │ ├── run_deepseek7b_llm_sp2.sh │ ├── run_deepseek_full_hh_rlhf.sh │ ├── run_deepseek_math_gsm8k_megatron.sh │ ├── run_gemma.sh │ ├── run_moonlight16b_a3b_gsm8k_megatron.sh │ ├── run_qwen1.5_moe_a2.7b-gsm8k_megatron.sh │ ├── run_qwen2-7b_math_gsm8k_megatron.sh │ ├── run_qwen2-7b_rm.sh │ ├── run_qwen2-7b_rm_seq_balance.sh │ ├── run_qwen2-7b_rm_seq_balance_fused_kernels.sh │ ├── run_qwen2-7b_seq_balance.sh │ ├── run_qwen2-7b_sglang_seq_balance.sh │ └── run_qwen2.5-32b.sh ├── ray │ └── tutorial.ipynb ├── reinforce_plus_plus_trainer │ ├── run_qwen2-7b_math_rf.sh │ └── run_qwen2-7b_math_rf_baseline.sh ├── remax_trainer │ ├── run_qwen2.5-3b_seq_balance.sh │ └── run_qwen2.5-7b_seq_balance.sh ├── rloo_trainer │ └── run_qwen2-7b.sh ├── sft │ ├── gsm8k │ │ ├── run_deepseek_6b7.sh │ │ ├── run_gemma_2b.sh │ │ ├── run_gemma_7b.sh │ │ ├── run_qwen_05_peft.sh │ │ ├── run_qwen_05_sp2.sh │ │ └── run_qwen_05_sp2_liger.sh │ └── multiturn │ │ └── run_qwen_05_sp2.sh ├── sglang_multiturn │ ├── README.md │ ├── config │ │ ├── gsm8k_multiturn_grpo.yaml │ │ ├── gsm8k_multiturn_megatron_grpo.yaml │ │ ├── retool_multiturn_grpo.yaml │ │ ├── search_multiturn_grpo.yaml │ │ └── tool_config │ │ │ ├── gsm8k_tool_config.yaml │ │ │ ├── sandbox_fusion_tool_config.yaml │ │ │ └── search_tool_config.yaml │ ├── run_qwen2.5-3b_gsm8k_multiturn.sh │ ├── run_qwen2.5-3b_gsm8k_multiturn_4xgpu.sh │ ├── run_qwen2.5-3b_megatron_gsm8k_multiturn.sh │ ├── run_qwen3-4b_gsm8k_multiturn.sh │ └── search_r1_like │ │ ├── local_dense_retriever │ │ ├── download.py │ │ └── retrieval_server.py │ │ └── run_qwen2.5-3b_instruct_search_multiturn.sh ├── slurm │ └── ray_on_slurm.slurm ├── split_placement │ ├── README.md │ ├── config │ │ └── ppo_trainer_split.yaml │ ├── main_ppo_split.py │ ├── run_deepseek7b_llm.sh │ └── split_monkey_patch.py └── tuning │ ├── 0.5b │ └── qwen2-0.5b_grpo-lora_1_h100_fsdp_vllm.sh │ ├── 1.5b │ └── qwen2-1.5b_grpo-lora_1_h100_fsdp_vllm.sh │ ├── 14b │ ├── qwen2-14b_grpo-lora_2_h100_fsdp_vllm.sh │ └── qwen2_14b_grpo_4_h800_fsdp_vllm.sh │ ├── 32b │ ├── qwen2-32b_grpo-lora_4_h100_fsdp_vllm.sh │ └── qwen2_32B_grpo_8_h20_megatron_vllm.sh │ ├── 3b │ └── qwen2-3b_grpo-lora_1_h100_fsdp_vllm.sh │ ├── 70b │ ├── qwen2-70b_grpo_32_h20_fsdp_vllm.sh │ ├── qwen2-70b_grpo_32_h800_fsdp_vllm.sh │ └── qwen2-72b_grpo-lora_8_h100_fsdp_vllm.sh │ └── 7b │ ├── qwen2-7b_grpo-lora_1_h100_fsdp_vllm.sh │ └── qwen2-7b_grpo_2_h800_fsdp_vllm.sh ├── pyproject.toml ├── recipe ├── README.md ├── char_count │ ├── README.md │ ├── create_dataset.py │ ├── reward_function.py │ ├── train_grpo.sh │ └── train_sft.sh ├── dapo │ ├── README.md │ ├── config │ │ └── dapo_trainer.yaml │ ├── dapo_ray_trainer.py │ ├── main_dapo.py │ ├── prepare_dapo_data.sh │ ├── run_dapo_early_qwen2.5_32b.sh │ ├── run_dapo_qwen2.5_32b.sh │ ├── run_dapo_wo_ds_qwen2.5_32b.sh │ ├── test_dapo_7b.sh │ ├── test_dapo_7b_math.sh │ ├── test_dapo_7b_math_lora.sh │ ├── test_dapo_7b_math_megatron.sh │ ├── test_dapo_dspk_671b_megatron.sh │ └── test_dapo_qwen3_30b_math.sh ├── prime │ ├── __init__.py │ ├── config │ │ └── prime_trainer.yaml │ ├── main_prime.py │ ├── prime_core_algos.py │ ├── prime_dp_rm.py │ ├── prime_fsdp_workers.py │ ├── prime_ray_trainer.py │ ├── run_prime_qwen.sh │ └── run_prime_qwen_code.sh ├── r1 │ ├── README.md │ ├── __init__.py │ ├── config │ │ └── evaluation.yaml │ ├── data_process.py │ ├── main_eval.py │ ├── reward_score.py │ ├── run_r1_distill_qwen.sh │ └── tasks │ │ ├── __init__.py │ │ ├── gpqa.py │ │ ├── livecodebench.py │ │ └── math.py ├── retool │ ├── retool_multi_turn_sft_preprocess.py │ ├── run_qwen2.5_32b_sp8.sh │ ├── run_qwen2.5_7b_sp4.sh │ ├── run_qwen3_4b_sp4.sh │ └── run_sft.sh ├── spin │ ├── README.md │ ├── config │ │ └── spin_trainer.yaml │ ├── core_algos.py │ ├── dp_actor.py │ ├── fsdp_workers.py │ ├── main_spin.py │ ├── run_spin.sh │ └── spin_trainer.py └── sppo │ ├── README.md │ ├── __init__.py │ ├── config │ └── sppo_trainer.yaml │ ├── dp_actor.py │ ├── main_sppo.py │ ├── run_qwen2.5-7b_rm.sh │ ├── sppo_ray_trainer.py │ └── sppo_worker.py ├── requirements-npu.txt ├── requirements.txt ├── requirements_sglang.txt ├── scripts ├── converter_hf_to_mcore.py ├── diagnose.py ├── init_random_model.py ├── install_vllm_sglang_mcore.sh └── model_merger.py ├── setup.py ├── tests ├── README.md ├── __init__.py ├── kill_github_tests.sh ├── models │ ├── test_transformer.py │ └── test_transformers_ulysses.py ├── single_controller │ ├── __init__.py │ ├── base │ │ └── test_decorator.py │ ├── check_worker_alive │ │ └── main.py │ ├── detached_worker │ │ ├── README.md │ │ ├── client.py │ │ ├── run.sh │ │ └── server.py │ ├── test_auto_padding_on_cpu.py │ ├── test_colocated_workers.py │ ├── test_colocated_workers_fused.py │ ├── test_data_transfer.py │ ├── test_decorator_on_cpu.py │ ├── test_driverfunc_to_worker.py │ ├── test_fused_workers_on_cpu.py │ ├── test_high_level_scheduling_api.py │ ├── test_ray_local_envs_on_cpu.py │ ├── test_ray_utils_on_cpu.py │ ├── test_rvdz.py │ ├── test_worker_group_basics.py │ └── test_worker_group_torch.py ├── special_distributed │ ├── README.md │ ├── run_all.sh │ ├── test_fsdp_ckpt.py │ └── test_tensor_dict.py ├── special_e2e │ ├── README.md │ ├── __init__.py │ ├── check_custom_rwd_fn.py │ ├── check_results.py │ ├── envs │ │ ├── __init__.py │ │ └── digit_completion │ │ │ ├── __init__.py │ │ │ ├── task.py │ │ │ └── tokenizer.py │ ├── generation │ │ └── run_gen_qwen05.sh │ ├── ppo_trainer │ │ ├── expert_parallel │ │ │ └── qwen2moe_minimal.json │ │ ├── run_function_reward.sh │ │ └── run_model_reward.sh │ ├── run_dapo.sh │ ├── run_grpo_lora_with_merge.sh │ ├── run_gsm8k_fsdp_sgl_multiturn_sf_tool.sh │ ├── run_gsm8k_fsdp_sgl_multiturn_w_tool.sh │ ├── run_ppo_trainer_megatron.sh │ ├── run_prime.sh │ ├── run_r1_distill_qwen_aime24_eval.sh │ ├── run_spin.sh │ ├── run_sppo.sh │ ├── run_test.sh │ └── sft │ │ ├── run_sft.sh │ │ └── test_sp_loss_match.py ├── special_npu │ ├── run_qwen2_5_05b_dapo.sh │ ├── run_qwen2_5_05b_grpo.sh │ ├── run_qwen2_5_32b_grpo.sh │ └── run_qwen2_5_7b_grpo.sh ├── special_sanity │ ├── check_license.py │ ├── check_pr_title.py │ ├── test_config_docs.py │ ├── test_import.py │ ├── type_coverage_check.py │ ├── validate_imported_docs.py │ └── validate_structure.py ├── special_standalone │ ├── README.md │ └── test_memory_buffers.py ├── test_protocol_on_cpu.py ├── trainer │ ├── __init__.py │ └── ppo │ │ ├── __init__.py │ │ ├── test_core_algos_on_cpu.py │ │ └── test_metric_utils_on_cpu.py ├── utils │ ├── _test_module.py │ ├── dataset │ │ ├── test_multiturn_sft_dataset_on_cpu.py │ │ ├── test_rl_dataset_on_cpu.py │ │ └── test_sft_dataset_on_cpu.py │ ├── megatron │ │ └── test_pipeline_parallel.py │ ├── reward_score │ │ ├── reward_score │ │ │ └── test_sandbox_fusion_on_cpu.py │ │ └── test_sandbox_on_cpu.py │ ├── test_activation_offload.py │ ├── test_flops_counter.py │ ├── test_fs_on_cpu.py │ ├── test_import_utils_on_cpu.py │ ├── test_linear_cross_entropy.py │ ├── test_linear_cross_entropy_tp.py │ ├── test_model_on_cpu.py │ ├── test_seqlen_balancing.py │ ├── test_timeout_decorator_cpu.py │ └── test_torch_functional.py └── workers │ ├── reward_manager │ └── test_registry_on_cpu.py │ └── rollout │ ├── async_rollout_utils.py │ ├── perf │ └── vllm_async_rollout.py │ ├── resource │ └── tool_configs │ │ ├── sandbox_fusion_tool_config │ │ └── search_tool_config │ ├── rollout_vllm │ ├── run_fsdp_vllm.py │ ├── test_vllm_chat_scheduler.py │ ├── test_vllm_hf_loader.py │ └── test_vllm_spmd.py │ ├── test_async_sglang_server.py │ ├── test_custom_completion_callback.py │ ├── test_hf_rollout.py │ ├── test_sglang_async_rollout_search_tools.py │ ├── test_sglang_async_rollout_sf_tools.py │ ├── test_sglang_async_rollout_w_tools.py │ ├── test_sglang_spmd.py │ └── utils_sglang.py └── verl ├── .DS_Store ├── __init__.py ├── models ├── README.md ├── __init__.py ├── llama │ ├── __init__.py │ └── megatron │ │ ├── __init__.py │ │ ├── checkpoint_utils │ │ ├── __init__.py │ │ ├── llama_loader.py │ │ ├── llama_loader_depracated.py │ │ └── llama_saver.py │ │ ├── layers │ │ ├── __init__.py │ │ ├── parallel_attention.py │ │ ├── parallel_decoder.py │ │ ├── parallel_linear.py │ │ ├── parallel_mlp.py │ │ └── parallel_rmsnorm.py │ │ └── modeling_llama_megatron.py ├── mcore │ ├── __init__.py │ ├── config_converter.py │ ├── loader.py │ ├── model_forward.py │ ├── model_initializer.py │ ├── patch_v012.py │ ├── qwen2_5_vl │ │ ├── __init__.py │ │ ├── attention.py │ │ ├── model.py │ │ ├── rope_utils.py │ │ ├── vision_config.py │ │ ├── vision_model.py │ │ └── vision_transformer_block.py │ ├── readme.md │ ├── registry.py │ ├── saver.py │ ├── util.py │ └── weight_converter.py ├── qwen2 │ ├── __init__.py │ └── megatron │ │ ├── __init__.py │ │ ├── checkpoint_utils │ │ ├── __init__.py │ │ ├── qwen2_loader.py │ │ ├── qwen2_loader_depracated.py │ │ └── qwen2_saver.py │ │ ├── layers │ │ ├── __init__.py │ │ ├── parallel_attention.py │ │ ├── parallel_decoder.py │ │ ├── parallel_linear.py │ │ ├── parallel_mlp.py │ │ └── parallel_rmsnorm.py │ │ └── modeling_qwen2_megatron.py ├── registry.py ├── transformers │ ├── __init__.py │ ├── dense_common.py │ ├── kimi_vl.py │ ├── llama.py │ ├── monkey_patch.py │ ├── qwen2.py │ ├── qwen2_5_vl.py │ └── qwen2_vl.py └── weight_loader_registry.py ├── protocol.py ├── single_controller ├── __init__.py ├── base │ ├── __init__.py │ ├── decorator.py │ ├── megatron │ │ ├── __init__.py │ │ ├── worker.py │ │ └── worker_group.py │ ├── register_center │ │ ├── __init__.py │ │ └── ray.py │ ├── worker.py │ └── worker_group.py └── ray │ ├── __init__.py │ ├── base.py │ └── megatron.py ├── third_party ├── __init__.py ├── sglang │ ├── __init__.py │ └── parallel_state.py └── vllm │ ├── __init__.py │ ├── vllm_v_0_5_4 │ ├── __init__.py │ ├── arg_utils.py │ ├── config.py │ ├── dtensor_weight_loaders.py │ ├── hf_weight_loader.py │ ├── llm.py │ ├── llm_engine_sp.py │ ├── megatron_weight_loaders.py │ ├── model_loader.py │ ├── model_runner.py │ ├── parallel_state.py │ ├── spmd_gpu_executor.py │ ├── tokenizer.py │ └── worker.py │ └── vllm_v_0_6_3 │ ├── __init__.py │ ├── arg_utils.py │ ├── config.py │ ├── dtensor_weight_loaders.py │ ├── hf_weight_loader.py │ ├── llm.py │ ├── llm_engine_sp.py │ ├── megatron_weight_loaders.py │ ├── model_loader.py │ ├── model_runner.py │ ├── parallel_state.py │ ├── spmd_gpu_executor.py │ ├── tokenizer.py │ └── worker.py ├── tools ├── .DS_Store ├── __init__.py ├── base_tool.py ├── config │ ├── search_tool_config.yaml │ ├── video_tool_config.yaml │ ├── video_tool_config_1getframe.yaml │ ├── video_tool_config_2getcaption.yaml │ ├── video_tool_config_3askquestion.yaml │ ├── zoom_tool_config.yaml │ ├── zoom_tool_config_2getcaption.yaml │ ├── zoom_tool_config_3askquestion.yaml │ ├── zoom_tool_config_new.yaml │ └── zoom_tool_config_new_all_for_paper.yaml ├── gsm8k_tool.py ├── sandbox_fusion_tools.py ├── schemas.py ├── search_tool.py ├── utils │ ├── __init__.py │ └── search_r1_like_utils.py ├── video_tools.py ├── zoom_tool.py └── zoom_tool_new.py ├── trainer ├── .DS_Store ├── __init__.py ├── config │ ├── evaluation.yaml │ ├── generation.yaml │ ├── ppo_megatron_trainer.yaml │ ├── ppo_trainer.yaml │ └── sft_trainer.yaml ├── fsdp_sft_trainer.py ├── main_eval.py ├── main_generation.py ├── main_ppo.py ├── ppo │ ├── __init__.py │ ├── core_algos.py │ ├── metric_utils.py │ ├── ray_trainer.py │ └── reward.py └── runtime_env.yaml ├── utils ├── .DS_Store ├── __init__.py ├── activation_offload.py ├── checkpoint │ ├── __init__.py │ ├── checkpoint_manager.py │ ├── fsdp_checkpoint_manager.py │ └── megatron_checkpoint_manager.py ├── config.py ├── dataset │ ├── DejaVuSans-Bold.ttf │ ├── README.md │ ├── __init__.py │ ├── multiturn_sft_dataset.py │ ├── rl_dataset.py │ ├── rl_dataset_multi_turn.py │ ├── rl_sampler_multimodal.py │ ├── rm_dataset.py │ ├── sampler.py │ ├── sft_dataset.py │ ├── sft_dataset_multi_turn.py │ ├── video_vl_utils.py │ └── vision_utils.py ├── debug │ ├── __init__.py │ ├── performance.py │ ├── profile.py │ └── trajectory_tracker.py ├── device.py ├── distributed.py ├── experimental │ ├── __init__.py │ └── torch_functional.py ├── flops_counter.py ├── fs.py ├── fsdp_utils.py ├── hdfs_io.py ├── import_utils.py ├── kernel │ ├── __init__.py │ ├── kernels.py │ └── linear_cross_entropy.py ├── logger │ ├── __init__.py │ └── aggregate_logger.py ├── logging_utils.py ├── megatron │ ├── __init__.py │ ├── memory.py │ ├── optimizer.py │ ├── pipeline_parallel.py │ ├── sequence_parallel.py │ └── tensor_parallel.py ├── megatron_utils.py ├── memory_buffer.py ├── metric │ ├── __init__.py │ └── utils.py ├── model.py ├── net_utils.py ├── py_functional.py ├── ray_utils.py ├── rendezvous │ ├── __init__.py │ └── ray_backend.py ├── reward_score │ ├── .DS_Store │ ├── __init__.py │ ├── charades.py │ ├── charades_cutreward.py │ ├── geo3k.py │ ├── gqa.py │ ├── gqa_cutreward.py │ ├── gsm8k.py │ ├── math.py │ ├── math_batch.py │ ├── math_dapo.py │ ├── math_verify.py │ ├── prime_code │ │ ├── __init__.py │ │ ├── testing_util.py │ │ └── utils.py │ ├── prime_math │ │ ├── __init__.py │ │ ├── grader.py │ │ └── math_normalize.py │ ├── sandbox_fusion │ │ ├── __init__.py │ │ └── utils.py │ ├── search_r1_like_qa_em.py │ ├── vidchapter_cutreward.py │ └── video_r1.py ├── seqlen_balancing.py ├── tokenizer.py ├── torch_dtypes.py ├── torch_functional.py ├── tracking.py ├── ulysses.py └── vllm_utils.py ├── version └── version └── workers ├── .DS_Store ├── __init__.py ├── actor ├── __init__.py ├── base.py ├── dp_actor.py └── megatron_actor.py ├── critic ├── __init__.py ├── base.py ├── dp_critic.py └── megatron_critic.py ├── fsdp_workers.py ├── megatron_workers.py ├── reward_manager ├── __init__.py ├── batch.py ├── dapo.py ├── naive.py ├── naive_multiturn.py ├── prime.py ├── prime_multiturn.py └── registry.py ├── reward_model ├── __init__.py ├── base.py └── megatron │ ├── __init__.py │ └── reward_model.py ├── rollout ├── .DS_Store ├── __init__.py ├── async_server.py ├── base.py ├── chat_scheduler.py ├── hf_rollout.py ├── naive │ ├── __init__.py │ └── naive_rollout.py ├── schemas.py ├── sglang_rollout │ ├── __init__.py │ ├── async_sglang_server.py │ ├── sglang_rollout.py │ └── utils.py ├── tokenizer.py └── vllm_rollout │ ├── __init__.py │ ├── fire_vllm_rollout.py │ ├── vllm_async_server.py │ ├── vllm_rollout.py │ ├── vllm_rollout_spmd.py │ ├── vllm_rollout_spmd_multi_turn.py │ └── vllm_rollout_spmd_multi_turn_sync.py └── sharding_manager ├── __init__.py ├── base.py ├── fsdp_sglang.py ├── fsdp_ulysses.py ├── fsdp_vllm.py ├── megatron_sglang.py └── megatron_vllm.py /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/README.md -------------------------------------------------------------------------------- /assets/framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/assets/framework.png -------------------------------------------------------------------------------- /data/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/data/.DS_Store -------------------------------------------------------------------------------- /eval_GQA.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/eval_GQA.py -------------------------------------------------------------------------------- /eval_VQA.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/eval_VQA.py -------------------------------------------------------------------------------- /eval_prompts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/eval_prompts.py -------------------------------------------------------------------------------- /eval_reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/eval_reward.py -------------------------------------------------------------------------------- /eval_temporal_grounding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/eval_temporal_grounding.py -------------------------------------------------------------------------------- /eval_temporal_grounding_multi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/eval_temporal_grounding_multi.py -------------------------------------------------------------------------------- /inference_vllm_multiturn_number.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/inference_vllm_multiturn_number.py -------------------------------------------------------------------------------- /inference_vllm_origin.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/inference_vllm_origin.py -------------------------------------------------------------------------------- /inference_vllm_origin_number.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/inference_vllm_origin_number.py -------------------------------------------------------------------------------- /setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/setup.sh -------------------------------------------------------------------------------- /train_stage_1_sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/train_stage_1_sft.sh -------------------------------------------------------------------------------- /train_stage_2_dgrpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/train_stage_2_dgrpo.sh -------------------------------------------------------------------------------- /train_stage_3_sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/train_stage_3_sft.sh -------------------------------------------------------------------------------- /train_stage_4_dgrpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/train_stage_4_dgrpo.sh -------------------------------------------------------------------------------- /verl/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/.DS_Store -------------------------------------------------------------------------------- /verl/.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/.pre-commit-config.yaml -------------------------------------------------------------------------------- /verl/.readthedocs.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/.readthedocs.yaml -------------------------------------------------------------------------------- /verl/BytedDockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/BytedDockerfile -------------------------------------------------------------------------------- /verl/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/LICENSE -------------------------------------------------------------------------------- /verl/Notice.txt: -------------------------------------------------------------------------------- 1 | Copyright 2023-2024 Bytedance Ltd. and/or its affiliates -------------------------------------------------------------------------------- /verl/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/README.md -------------------------------------------------------------------------------- /verl/docker/Apptainerfile.rocm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docker/Apptainerfile.rocm -------------------------------------------------------------------------------- /verl/docker/Dockerfile.awsefa: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docker/Dockerfile.awsefa -------------------------------------------------------------------------------- /verl/docker/Dockerfile.ngc.vllm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docker/Dockerfile.ngc.vllm -------------------------------------------------------------------------------- /verl/docker/Dockerfile.ngc.vllm0.8: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docker/Dockerfile.ngc.vllm0.8 -------------------------------------------------------------------------------- /verl/docker/Dockerfile.ngc.vllm0.8.sagemaker: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docker/Dockerfile.ngc.vllm0.8.sagemaker -------------------------------------------------------------------------------- /verl/docker/Dockerfile.rocm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docker/Dockerfile.rocm -------------------------------------------------------------------------------- /verl/docker/Dockerfile.sglang: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docker/Dockerfile.sglang -------------------------------------------------------------------------------- /verl/docker/Dockerfile.vemlp.vllm.te: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docker/Dockerfile.vemlp.vllm.te -------------------------------------------------------------------------------- /verl/docker/Dockerfile.vllm.sglang.megatron: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docker/Dockerfile.vllm.sglang.megatron -------------------------------------------------------------------------------- /verl/docker/Dockerfile.vllm.sglang.megatron.deepseek: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docker/Dockerfile.vllm.sglang.megatron.deepseek -------------------------------------------------------------------------------- /verl/docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/Makefile -------------------------------------------------------------------------------- /verl/docs/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/README.md -------------------------------------------------------------------------------- /verl/docs/README_vllm0.7.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/README_vllm0.7.md -------------------------------------------------------------------------------- /verl/docs/README_vllm0.8.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/README_vllm0.8.md -------------------------------------------------------------------------------- /verl/docs/_static/js/runllm-widget.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/_static/js/runllm-widget.js -------------------------------------------------------------------------------- /verl/docs/_static/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/_static/logo.png -------------------------------------------------------------------------------- /verl/docs/advance/checkpoint.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/advance/checkpoint.rst -------------------------------------------------------------------------------- /verl/docs/advance/dpo_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/advance/dpo_extension.rst -------------------------------------------------------------------------------- /verl/docs/advance/fsdp_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/advance/fsdp_extension.rst -------------------------------------------------------------------------------- /verl/docs/advance/megatron_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/advance/megatron_extension.rst -------------------------------------------------------------------------------- /verl/docs/advance/placement.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/advance/placement.rst -------------------------------------------------------------------------------- /verl/docs/advance/ppo_lora.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/advance/ppo_lora.rst -------------------------------------------------------------------------------- /verl/docs/advance/rope.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/advance/rope.rst -------------------------------------------------------------------------------- /verl/docs/algo/baseline.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/algo/baseline.md -------------------------------------------------------------------------------- /verl/docs/algo/dapo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/algo/dapo.md -------------------------------------------------------------------------------- /verl/docs/algo/grpo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/algo/grpo.md -------------------------------------------------------------------------------- /verl/docs/algo/opo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/algo/opo.md -------------------------------------------------------------------------------- /verl/docs/algo/ppo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/algo/ppo.md -------------------------------------------------------------------------------- /verl/docs/algo/spin.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/algo/spin.md -------------------------------------------------------------------------------- /verl/docs/algo/sppo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/algo/sppo.md -------------------------------------------------------------------------------- /verl/docs/amd_tutorial/amd_build_dockerfile_page.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/amd_tutorial/amd_build_dockerfile_page.rst -------------------------------------------------------------------------------- /verl/docs/amd_tutorial/amd_vllm_page.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/amd_tutorial/amd_vllm_page.rst -------------------------------------------------------------------------------- /verl/docs/api/data.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/api/data.rst -------------------------------------------------------------------------------- /verl/docs/api/single_controller.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/api/single_controller.rst -------------------------------------------------------------------------------- /verl/docs/api/trainer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/api/trainer.rst -------------------------------------------------------------------------------- /verl/docs/api/utils.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/api/utils.rst -------------------------------------------------------------------------------- /verl/docs/ascend_tutorial/ascend_quick_start.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/ascend_tutorial/ascend_quick_start.rst -------------------------------------------------------------------------------- /verl/docs/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/conf.py -------------------------------------------------------------------------------- /verl/docs/examples/config.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/examples/config.rst -------------------------------------------------------------------------------- /verl/docs/examples/gsm8k_example.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/examples/gsm8k_example.rst -------------------------------------------------------------------------------- /verl/docs/examples/multi_modal_example.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/examples/multi_modal_example.rst -------------------------------------------------------------------------------- /verl/docs/examples/ppo_code_architecture.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/examples/ppo_code_architecture.rst -------------------------------------------------------------------------------- /verl/docs/examples/sandbox_fusion_example.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/examples/sandbox_fusion_example.rst -------------------------------------------------------------------------------- /verl/docs/faq/faq.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/faq/faq.rst -------------------------------------------------------------------------------- /verl/docs/hybrid_flow.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/hybrid_flow.rst -------------------------------------------------------------------------------- /verl/docs/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/index.rst -------------------------------------------------------------------------------- /verl/docs/perf/device_tuning.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/perf/device_tuning.rst -------------------------------------------------------------------------------- /verl/docs/perf/dpsk.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/perf/dpsk.md -------------------------------------------------------------------------------- /verl/docs/perf/perf_tuning.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/perf/perf_tuning.rst -------------------------------------------------------------------------------- /verl/docs/preparation/prepare_data.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/preparation/prepare_data.rst -------------------------------------------------------------------------------- /verl/docs/preparation/reward_function.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/preparation/reward_function.rst -------------------------------------------------------------------------------- /verl/docs/requirements-docs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/requirements-docs.txt -------------------------------------------------------------------------------- /verl/docs/sglang_multiturn/multiturn.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/sglang_multiturn/multiturn.rst -------------------------------------------------------------------------------- /verl/docs/sglang_multiturn/sandbox_fusion.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/sglang_multiturn/sandbox_fusion.rst -------------------------------------------------------------------------------- /verl/docs/sglang_multiturn/search_tool_example.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/sglang_multiturn/search_tool_example.rst -------------------------------------------------------------------------------- /verl/docs/single_controller.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/single_controller.rst -------------------------------------------------------------------------------- /verl/docs/start/install.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/start/install.rst -------------------------------------------------------------------------------- /verl/docs/start/multinode.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/start/multinode.rst -------------------------------------------------------------------------------- /verl/docs/start/quickstart.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/start/quickstart.rst -------------------------------------------------------------------------------- /verl/docs/start/ray_debug_tutorial.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/start/ray_debug_tutorial.rst -------------------------------------------------------------------------------- /verl/docs/workers/fsdp_workers.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/workers/fsdp_workers.rst -------------------------------------------------------------------------------- /verl/docs/workers/megatron_workers.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/workers/megatron_workers.rst -------------------------------------------------------------------------------- /verl/docs/workers/ray_trainer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/workers/ray_trainer.rst -------------------------------------------------------------------------------- /verl/docs/workers/sglang_worker.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/docs/workers/sglang_worker.rst -------------------------------------------------------------------------------- /verl/examples/data_preprocess/aime2024_multiturn_w_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/data_preprocess/aime2024_multiturn_w_tool.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/dapo_multiturn_w_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/data_preprocess/dapo_multiturn_w_tool.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/full_hh_rlhf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/data_preprocess/full_hh_rlhf.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/geo3k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/data_preprocess/geo3k.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/data_preprocess/gsm8k.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/gsm8k_multiturn_w_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/data_preprocess/gsm8k_multiturn_w_tool.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/hellaswag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/data_preprocess/hellaswag.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/math_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/data_preprocess/math_dataset.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/multiturn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/data_preprocess/multiturn.py -------------------------------------------------------------------------------- /verl/examples/data_preprocess/preprocess_search_r1_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/data_preprocess/preprocess_search_r1_dataset.py -------------------------------------------------------------------------------- /verl/examples/generation/run_deepseek7b_mutli_node.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/generation/run_deepseek7b_mutli_node.sh -------------------------------------------------------------------------------- /verl/examples/generation/run_deepseek_v2_lite_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/generation/run_deepseek_v2_lite_math.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/README.md -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_deepseek671b_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_deepseek671b_math_megatron.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_deepseek7b_llm_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_deepseek7b_llm_math.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_deepseek7b_llm_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_deepseek7b_llm_math_megatron.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_deepseek7b_llm_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_deepseek7b_llm_seq_balance.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_moonlight16b_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_moonlight16b_math_megatron.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_qwen2-7b.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2-7b_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_qwen2-7b_math.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2-7b_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_qwen2-7b_math_megatron.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_qwen2-7b_seq_balance.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2-7b_seq_balance_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_qwen2-7b_seq_balance_math_megatron.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2-7b_sgl_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_qwen2-7b_sgl_megatron.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2_5-3b_gsm8k_grpo_lora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_qwen2_5-3b_gsm8k_grpo_lora.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2_5-7b_math_megatron_diff_tp.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_qwen2_5-7b_math_megatron_diff_tp.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2_5_vl-7b-megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_qwen2_5_vl-7b-megatron.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen2_5_vl-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_qwen2_5_vl-7b.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen3-236b_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_qwen3-236b_megatron.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen3-8b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_qwen3-8b.sh -------------------------------------------------------------------------------- /verl/examples/grpo_trainer/run_qwen3moe-30b_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/grpo_trainer/run_qwen3moe-30b_megatron.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/README.md -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_deepseek7b_llm_modelscope.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_deepseek7b_llm_modelscope.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_deepseek7b_llm_pfppo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_deepseek7b_llm_pfppo.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_deepseek7b_llm_sandbox_fusion.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_deepseek7b_llm_sandbox_fusion.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_deepseek7b_llm_sp2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_deepseek7b_llm_sp2.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_deepseek_full_hh_rlhf.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_deepseek_full_hh_rlhf.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_deepseek_math_gsm8k_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_deepseek_math_gsm8k_megatron.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_gemma.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_gemma.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_moonlight16b_a3b_gsm8k_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_moonlight16b_a3b_gsm8k_megatron.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_qwen1.5_moe_a2.7b-gsm8k_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_qwen1.5_moe_a2.7b-gsm8k_megatron.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_qwen2-7b_math_gsm8k_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_qwen2-7b_math_gsm8k_megatron.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_qwen2-7b_rm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_qwen2-7b_rm.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_qwen2-7b_rm_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_qwen2-7b_rm_seq_balance.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_qwen2-7b_rm_seq_balance_fused_kernels.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_qwen2-7b_rm_seq_balance_fused_kernels.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_qwen2-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_qwen2-7b_seq_balance.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_qwen2-7b_sglang_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_qwen2-7b_sglang_seq_balance.sh -------------------------------------------------------------------------------- /verl/examples/ppo_trainer/run_qwen2.5-32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ppo_trainer/run_qwen2.5-32b.sh -------------------------------------------------------------------------------- /verl/examples/ray/tutorial.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/ray/tutorial.ipynb -------------------------------------------------------------------------------- /verl/examples/reinforce_plus_plus_trainer/run_qwen2-7b_math_rf.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/reinforce_plus_plus_trainer/run_qwen2-7b_math_rf.sh -------------------------------------------------------------------------------- /verl/examples/reinforce_plus_plus_trainer/run_qwen2-7b_math_rf_baseline.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/reinforce_plus_plus_trainer/run_qwen2-7b_math_rf_baseline.sh -------------------------------------------------------------------------------- /verl/examples/remax_trainer/run_qwen2.5-3b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/remax_trainer/run_qwen2.5-3b_seq_balance.sh -------------------------------------------------------------------------------- /verl/examples/remax_trainer/run_qwen2.5-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/remax_trainer/run_qwen2.5-7b_seq_balance.sh -------------------------------------------------------------------------------- /verl/examples/rloo_trainer/run_qwen2-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/rloo_trainer/run_qwen2-7b.sh -------------------------------------------------------------------------------- /verl/examples/sft/gsm8k/run_deepseek_6b7.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sft/gsm8k/run_deepseek_6b7.sh -------------------------------------------------------------------------------- /verl/examples/sft/gsm8k/run_gemma_2b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sft/gsm8k/run_gemma_2b.sh -------------------------------------------------------------------------------- /verl/examples/sft/gsm8k/run_gemma_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sft/gsm8k/run_gemma_7b.sh -------------------------------------------------------------------------------- /verl/examples/sft/gsm8k/run_qwen_05_peft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sft/gsm8k/run_qwen_05_peft.sh -------------------------------------------------------------------------------- /verl/examples/sft/gsm8k/run_qwen_05_sp2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sft/gsm8k/run_qwen_05_sp2.sh -------------------------------------------------------------------------------- /verl/examples/sft/gsm8k/run_qwen_05_sp2_liger.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sft/gsm8k/run_qwen_05_sp2_liger.sh -------------------------------------------------------------------------------- /verl/examples/sft/multiturn/run_qwen_05_sp2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sft/multiturn/run_qwen_05_sp2.sh -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/README.md -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/config/gsm8k_multiturn_grpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/config/gsm8k_multiturn_grpo.yaml -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/config/gsm8k_multiturn_megatron_grpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/config/gsm8k_multiturn_megatron_grpo.yaml -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/config/retool_multiturn_grpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/config/retool_multiturn_grpo.yaml -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/config/search_multiturn_grpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/config/search_multiturn_grpo.yaml -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/config/tool_config/gsm8k_tool_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/config/tool_config/gsm8k_tool_config.yaml -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/config/tool_config/sandbox_fusion_tool_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/config/tool_config/sandbox_fusion_tool_config.yaml -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/config/tool_config/search_tool_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/config/tool_config/search_tool_config.yaml -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/run_qwen2.5-3b_gsm8k_multiturn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/run_qwen2.5-3b_gsm8k_multiturn.sh -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/run_qwen2.5-3b_gsm8k_multiturn_4xgpu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/run_qwen2.5-3b_gsm8k_multiturn_4xgpu.sh -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/run_qwen2.5-3b_megatron_gsm8k_multiturn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/run_qwen2.5-3b_megatron_gsm8k_multiturn.sh -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/run_qwen3-4b_gsm8k_multiturn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/run_qwen3-4b_gsm8k_multiturn.sh -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/search_r1_like/local_dense_retriever/download.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/search_r1_like/local_dense_retriever/download.py -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/search_r1_like/local_dense_retriever/retrieval_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/search_r1_like/local_dense_retriever/retrieval_server.py -------------------------------------------------------------------------------- /verl/examples/sglang_multiturn/search_r1_like/run_qwen2.5-3b_instruct_search_multiturn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/sglang_multiturn/search_r1_like/run_qwen2.5-3b_instruct_search_multiturn.sh -------------------------------------------------------------------------------- /verl/examples/slurm/ray_on_slurm.slurm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/slurm/ray_on_slurm.slurm -------------------------------------------------------------------------------- /verl/examples/split_placement/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/split_placement/README.md -------------------------------------------------------------------------------- /verl/examples/split_placement/config/ppo_trainer_split.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/split_placement/config/ppo_trainer_split.yaml -------------------------------------------------------------------------------- /verl/examples/split_placement/main_ppo_split.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/split_placement/main_ppo_split.py -------------------------------------------------------------------------------- /verl/examples/split_placement/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/split_placement/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /verl/examples/split_placement/split_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/split_placement/split_monkey_patch.py -------------------------------------------------------------------------------- /verl/examples/tuning/0.5b/qwen2-0.5b_grpo-lora_1_h100_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/tuning/0.5b/qwen2-0.5b_grpo-lora_1_h100_fsdp_vllm.sh -------------------------------------------------------------------------------- /verl/examples/tuning/1.5b/qwen2-1.5b_grpo-lora_1_h100_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/tuning/1.5b/qwen2-1.5b_grpo-lora_1_h100_fsdp_vllm.sh -------------------------------------------------------------------------------- /verl/examples/tuning/14b/qwen2-14b_grpo-lora_2_h100_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/tuning/14b/qwen2-14b_grpo-lora_2_h100_fsdp_vllm.sh -------------------------------------------------------------------------------- /verl/examples/tuning/14b/qwen2_14b_grpo_4_h800_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/tuning/14b/qwen2_14b_grpo_4_h800_fsdp_vllm.sh -------------------------------------------------------------------------------- /verl/examples/tuning/32b/qwen2-32b_grpo-lora_4_h100_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/tuning/32b/qwen2-32b_grpo-lora_4_h100_fsdp_vllm.sh -------------------------------------------------------------------------------- /verl/examples/tuning/32b/qwen2_32B_grpo_8_h20_megatron_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/tuning/32b/qwen2_32B_grpo_8_h20_megatron_vllm.sh -------------------------------------------------------------------------------- /verl/examples/tuning/3b/qwen2-3b_grpo-lora_1_h100_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/tuning/3b/qwen2-3b_grpo-lora_1_h100_fsdp_vllm.sh -------------------------------------------------------------------------------- /verl/examples/tuning/70b/qwen2-70b_grpo_32_h20_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/tuning/70b/qwen2-70b_grpo_32_h20_fsdp_vllm.sh -------------------------------------------------------------------------------- /verl/examples/tuning/70b/qwen2-70b_grpo_32_h800_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/tuning/70b/qwen2-70b_grpo_32_h800_fsdp_vllm.sh -------------------------------------------------------------------------------- /verl/examples/tuning/70b/qwen2-72b_grpo-lora_8_h100_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/tuning/70b/qwen2-72b_grpo-lora_8_h100_fsdp_vllm.sh -------------------------------------------------------------------------------- /verl/examples/tuning/7b/qwen2-7b_grpo-lora_1_h100_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/tuning/7b/qwen2-7b_grpo-lora_1_h100_fsdp_vllm.sh -------------------------------------------------------------------------------- /verl/examples/tuning/7b/qwen2-7b_grpo_2_h800_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/examples/tuning/7b/qwen2-7b_grpo_2_h800_fsdp_vllm.sh -------------------------------------------------------------------------------- /verl/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/pyproject.toml -------------------------------------------------------------------------------- /verl/recipe/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/README.md -------------------------------------------------------------------------------- /verl/recipe/char_count/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/char_count/README.md -------------------------------------------------------------------------------- /verl/recipe/char_count/create_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/char_count/create_dataset.py -------------------------------------------------------------------------------- /verl/recipe/char_count/reward_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/char_count/reward_function.py -------------------------------------------------------------------------------- /verl/recipe/char_count/train_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/char_count/train_grpo.sh -------------------------------------------------------------------------------- /verl/recipe/char_count/train_sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/char_count/train_sft.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/dapo/README.md -------------------------------------------------------------------------------- /verl/recipe/dapo/config/dapo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/dapo/config/dapo_trainer.yaml -------------------------------------------------------------------------------- /verl/recipe/dapo/dapo_ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/dapo/dapo_ray_trainer.py -------------------------------------------------------------------------------- /verl/recipe/dapo/main_dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/dapo/main_dapo.py -------------------------------------------------------------------------------- /verl/recipe/dapo/prepare_dapo_data.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/dapo/prepare_dapo_data.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/run_dapo_early_qwen2.5_32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/dapo/run_dapo_early_qwen2.5_32b.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/run_dapo_qwen2.5_32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/dapo/run_dapo_qwen2.5_32b.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/run_dapo_wo_ds_qwen2.5_32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/dapo/run_dapo_wo_ds_qwen2.5_32b.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/test_dapo_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/dapo/test_dapo_7b.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/test_dapo_7b_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/dapo/test_dapo_7b_math.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/test_dapo_7b_math_lora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/dapo/test_dapo_7b_math_lora.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/test_dapo_7b_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/dapo/test_dapo_7b_math_megatron.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/test_dapo_dspk_671b_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/dapo/test_dapo_dspk_671b_megatron.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/test_dapo_qwen3_30b_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/dapo/test_dapo_qwen3_30b_math.sh -------------------------------------------------------------------------------- /verl/recipe/prime/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/prime/__init__.py -------------------------------------------------------------------------------- /verl/recipe/prime/config/prime_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/prime/config/prime_trainer.yaml -------------------------------------------------------------------------------- /verl/recipe/prime/main_prime.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/prime/main_prime.py -------------------------------------------------------------------------------- /verl/recipe/prime/prime_core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/prime/prime_core_algos.py -------------------------------------------------------------------------------- /verl/recipe/prime/prime_dp_rm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/prime/prime_dp_rm.py -------------------------------------------------------------------------------- /verl/recipe/prime/prime_fsdp_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/prime/prime_fsdp_workers.py -------------------------------------------------------------------------------- /verl/recipe/prime/prime_ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/prime/prime_ray_trainer.py -------------------------------------------------------------------------------- /verl/recipe/prime/run_prime_qwen.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/prime/run_prime_qwen.sh -------------------------------------------------------------------------------- /verl/recipe/prime/run_prime_qwen_code.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/prime/run_prime_qwen_code.sh -------------------------------------------------------------------------------- /verl/recipe/r1/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/r1/README.md -------------------------------------------------------------------------------- /verl/recipe/r1/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/r1/__init__.py -------------------------------------------------------------------------------- /verl/recipe/r1/config/evaluation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/r1/config/evaluation.yaml -------------------------------------------------------------------------------- /verl/recipe/r1/data_process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/r1/data_process.py -------------------------------------------------------------------------------- /verl/recipe/r1/main_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/r1/main_eval.py -------------------------------------------------------------------------------- /verl/recipe/r1/reward_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/r1/reward_score.py -------------------------------------------------------------------------------- /verl/recipe/r1/run_r1_distill_qwen.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/r1/run_r1_distill_qwen.sh -------------------------------------------------------------------------------- /verl/recipe/r1/tasks/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/r1/tasks/__init__.py -------------------------------------------------------------------------------- /verl/recipe/r1/tasks/gpqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/r1/tasks/gpqa.py -------------------------------------------------------------------------------- /verl/recipe/r1/tasks/livecodebench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/r1/tasks/livecodebench.py -------------------------------------------------------------------------------- /verl/recipe/r1/tasks/math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/r1/tasks/math.py -------------------------------------------------------------------------------- /verl/recipe/retool/retool_multi_turn_sft_preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/retool/retool_multi_turn_sft_preprocess.py -------------------------------------------------------------------------------- /verl/recipe/retool/run_qwen2.5_32b_sp8.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/retool/run_qwen2.5_32b_sp8.sh -------------------------------------------------------------------------------- /verl/recipe/retool/run_qwen2.5_7b_sp4.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/retool/run_qwen2.5_7b_sp4.sh -------------------------------------------------------------------------------- /verl/recipe/retool/run_qwen3_4b_sp4.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/retool/run_qwen3_4b_sp4.sh -------------------------------------------------------------------------------- /verl/recipe/retool/run_sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/retool/run_sft.sh -------------------------------------------------------------------------------- /verl/recipe/spin/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/spin/README.md -------------------------------------------------------------------------------- /verl/recipe/spin/config/spin_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/spin/config/spin_trainer.yaml -------------------------------------------------------------------------------- /verl/recipe/spin/core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/spin/core_algos.py -------------------------------------------------------------------------------- /verl/recipe/spin/dp_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/spin/dp_actor.py -------------------------------------------------------------------------------- /verl/recipe/spin/fsdp_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/spin/fsdp_workers.py -------------------------------------------------------------------------------- /verl/recipe/spin/main_spin.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/spin/main_spin.py -------------------------------------------------------------------------------- /verl/recipe/spin/run_spin.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/spin/run_spin.sh -------------------------------------------------------------------------------- /verl/recipe/spin/spin_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/spin/spin_trainer.py -------------------------------------------------------------------------------- /verl/recipe/sppo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/sppo/README.md -------------------------------------------------------------------------------- /verl/recipe/sppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/sppo/__init__.py -------------------------------------------------------------------------------- /verl/recipe/sppo/config/sppo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/sppo/config/sppo_trainer.yaml -------------------------------------------------------------------------------- /verl/recipe/sppo/dp_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/sppo/dp_actor.py -------------------------------------------------------------------------------- /verl/recipe/sppo/main_sppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/sppo/main_sppo.py -------------------------------------------------------------------------------- /verl/recipe/sppo/run_qwen2.5-7b_rm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/sppo/run_qwen2.5-7b_rm.sh -------------------------------------------------------------------------------- /verl/recipe/sppo/sppo_ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/sppo/sppo_ray_trainer.py -------------------------------------------------------------------------------- /verl/recipe/sppo/sppo_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/recipe/sppo/sppo_worker.py -------------------------------------------------------------------------------- /verl/requirements-npu.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/requirements-npu.txt -------------------------------------------------------------------------------- /verl/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/requirements.txt -------------------------------------------------------------------------------- /verl/requirements_sglang.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/requirements_sglang.txt -------------------------------------------------------------------------------- /verl/scripts/converter_hf_to_mcore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/scripts/converter_hf_to_mcore.py -------------------------------------------------------------------------------- /verl/scripts/diagnose.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/scripts/diagnose.py -------------------------------------------------------------------------------- /verl/scripts/init_random_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/scripts/init_random_model.py -------------------------------------------------------------------------------- /verl/scripts/install_vllm_sglang_mcore.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/scripts/install_vllm_sglang_mcore.sh -------------------------------------------------------------------------------- /verl/scripts/model_merger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/scripts/model_merger.py -------------------------------------------------------------------------------- /verl/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/setup.py -------------------------------------------------------------------------------- /verl/tests/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/README.md -------------------------------------------------------------------------------- /verl/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/__init__.py -------------------------------------------------------------------------------- /verl/tests/kill_github_tests.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/kill_github_tests.sh -------------------------------------------------------------------------------- /verl/tests/models/test_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/models/test_transformer.py -------------------------------------------------------------------------------- /verl/tests/models/test_transformers_ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/models/test_transformers_ulysses.py -------------------------------------------------------------------------------- /verl/tests/single_controller/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/__init__.py -------------------------------------------------------------------------------- /verl/tests/single_controller/base/test_decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/base/test_decorator.py -------------------------------------------------------------------------------- /verl/tests/single_controller/check_worker_alive/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/check_worker_alive/main.py -------------------------------------------------------------------------------- /verl/tests/single_controller/detached_worker/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/detached_worker/README.md -------------------------------------------------------------------------------- /verl/tests/single_controller/detached_worker/client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/detached_worker/client.py -------------------------------------------------------------------------------- /verl/tests/single_controller/detached_worker/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/detached_worker/run.sh -------------------------------------------------------------------------------- /verl/tests/single_controller/detached_worker/server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/detached_worker/server.py -------------------------------------------------------------------------------- /verl/tests/single_controller/test_auto_padding_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/test_auto_padding_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/single_controller/test_colocated_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/test_colocated_workers.py -------------------------------------------------------------------------------- /verl/tests/single_controller/test_colocated_workers_fused.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/test_colocated_workers_fused.py -------------------------------------------------------------------------------- /verl/tests/single_controller/test_data_transfer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/test_data_transfer.py -------------------------------------------------------------------------------- /verl/tests/single_controller/test_decorator_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/test_decorator_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/single_controller/test_driverfunc_to_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/test_driverfunc_to_worker.py -------------------------------------------------------------------------------- /verl/tests/single_controller/test_fused_workers_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/test_fused_workers_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/single_controller/test_high_level_scheduling_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/test_high_level_scheduling_api.py -------------------------------------------------------------------------------- /verl/tests/single_controller/test_ray_local_envs_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/test_ray_local_envs_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/single_controller/test_ray_utils_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/test_ray_utils_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/single_controller/test_rvdz.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/test_rvdz.py -------------------------------------------------------------------------------- /verl/tests/single_controller/test_worker_group_basics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/test_worker_group_basics.py -------------------------------------------------------------------------------- /verl/tests/single_controller/test_worker_group_torch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/single_controller/test_worker_group_torch.py -------------------------------------------------------------------------------- /verl/tests/special_distributed/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_distributed/README.md -------------------------------------------------------------------------------- /verl/tests/special_distributed/run_all.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_distributed/run_all.sh -------------------------------------------------------------------------------- /verl/tests/special_distributed/test_fsdp_ckpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_distributed/test_fsdp_ckpt.py -------------------------------------------------------------------------------- /verl/tests/special_distributed/test_tensor_dict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_distributed/test_tensor_dict.py -------------------------------------------------------------------------------- /verl/tests/special_e2e/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/README.md -------------------------------------------------------------------------------- /verl/tests/special_e2e/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/__init__.py -------------------------------------------------------------------------------- /verl/tests/special_e2e/check_custom_rwd_fn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/check_custom_rwd_fn.py -------------------------------------------------------------------------------- /verl/tests/special_e2e/check_results.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/check_results.py -------------------------------------------------------------------------------- /verl/tests/special_e2e/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/envs/__init__.py -------------------------------------------------------------------------------- /verl/tests/special_e2e/envs/digit_completion/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/envs/digit_completion/__init__.py -------------------------------------------------------------------------------- /verl/tests/special_e2e/envs/digit_completion/task.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/envs/digit_completion/task.py -------------------------------------------------------------------------------- /verl/tests/special_e2e/envs/digit_completion/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/envs/digit_completion/tokenizer.py -------------------------------------------------------------------------------- /verl/tests/special_e2e/generation/run_gen_qwen05.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/generation/run_gen_qwen05.sh -------------------------------------------------------------------------------- /verl/tests/special_e2e/ppo_trainer/expert_parallel/qwen2moe_minimal.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/ppo_trainer/expert_parallel/qwen2moe_minimal.json -------------------------------------------------------------------------------- /verl/tests/special_e2e/ppo_trainer/run_function_reward.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/ppo_trainer/run_function_reward.sh -------------------------------------------------------------------------------- /verl/tests/special_e2e/ppo_trainer/run_model_reward.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/ppo_trainer/run_model_reward.sh -------------------------------------------------------------------------------- /verl/tests/special_e2e/run_dapo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/run_dapo.sh -------------------------------------------------------------------------------- /verl/tests/special_e2e/run_grpo_lora_with_merge.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/run_grpo_lora_with_merge.sh -------------------------------------------------------------------------------- /verl/tests/special_e2e/run_gsm8k_fsdp_sgl_multiturn_sf_tool.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/run_gsm8k_fsdp_sgl_multiturn_sf_tool.sh -------------------------------------------------------------------------------- /verl/tests/special_e2e/run_gsm8k_fsdp_sgl_multiturn_w_tool.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/run_gsm8k_fsdp_sgl_multiturn_w_tool.sh -------------------------------------------------------------------------------- /verl/tests/special_e2e/run_ppo_trainer_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/run_ppo_trainer_megatron.sh -------------------------------------------------------------------------------- /verl/tests/special_e2e/run_prime.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/run_prime.sh -------------------------------------------------------------------------------- /verl/tests/special_e2e/run_r1_distill_qwen_aime24_eval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/run_r1_distill_qwen_aime24_eval.sh -------------------------------------------------------------------------------- /verl/tests/special_e2e/run_spin.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/run_spin.sh -------------------------------------------------------------------------------- /verl/tests/special_e2e/run_sppo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/run_sppo.sh -------------------------------------------------------------------------------- /verl/tests/special_e2e/run_test.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/run_test.sh -------------------------------------------------------------------------------- /verl/tests/special_e2e/sft/run_sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/sft/run_sft.sh -------------------------------------------------------------------------------- /verl/tests/special_e2e/sft/test_sp_loss_match.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_e2e/sft/test_sp_loss_match.py -------------------------------------------------------------------------------- /verl/tests/special_npu/run_qwen2_5_05b_dapo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_npu/run_qwen2_5_05b_dapo.sh -------------------------------------------------------------------------------- /verl/tests/special_npu/run_qwen2_5_05b_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_npu/run_qwen2_5_05b_grpo.sh -------------------------------------------------------------------------------- /verl/tests/special_npu/run_qwen2_5_32b_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_npu/run_qwen2_5_32b_grpo.sh -------------------------------------------------------------------------------- /verl/tests/special_npu/run_qwen2_5_7b_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_npu/run_qwen2_5_7b_grpo.sh -------------------------------------------------------------------------------- /verl/tests/special_sanity/check_license.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_sanity/check_license.py -------------------------------------------------------------------------------- /verl/tests/special_sanity/check_pr_title.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_sanity/check_pr_title.py -------------------------------------------------------------------------------- /verl/tests/special_sanity/test_config_docs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_sanity/test_config_docs.py -------------------------------------------------------------------------------- /verl/tests/special_sanity/test_import.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_sanity/test_import.py -------------------------------------------------------------------------------- /verl/tests/special_sanity/type_coverage_check.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_sanity/type_coverage_check.py -------------------------------------------------------------------------------- /verl/tests/special_sanity/validate_imported_docs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_sanity/validate_imported_docs.py -------------------------------------------------------------------------------- /verl/tests/special_sanity/validate_structure.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_sanity/validate_structure.py -------------------------------------------------------------------------------- /verl/tests/special_standalone/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_standalone/README.md -------------------------------------------------------------------------------- /verl/tests/special_standalone/test_memory_buffers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/special_standalone/test_memory_buffers.py -------------------------------------------------------------------------------- /verl/tests/test_protocol_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/test_protocol_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/trainer/__init__.py -------------------------------------------------------------------------------- /verl/tests/trainer/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/trainer/ppo/__init__.py -------------------------------------------------------------------------------- /verl/tests/trainer/ppo/test_core_algos_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/trainer/ppo/test_core_algos_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/trainer/ppo/test_metric_utils_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/trainer/ppo/test_metric_utils_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/utils/_test_module.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/_test_module.py -------------------------------------------------------------------------------- /verl/tests/utils/dataset/test_multiturn_sft_dataset_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/dataset/test_multiturn_sft_dataset_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/utils/dataset/test_rl_dataset_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/dataset/test_rl_dataset_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/utils/dataset/test_sft_dataset_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/dataset/test_sft_dataset_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/utils/megatron/test_pipeline_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/megatron/test_pipeline_parallel.py -------------------------------------------------------------------------------- /verl/tests/utils/reward_score/reward_score/test_sandbox_fusion_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/reward_score/reward_score/test_sandbox_fusion_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/utils/reward_score/test_sandbox_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/reward_score/test_sandbox_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/utils/test_activation_offload.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/test_activation_offload.py -------------------------------------------------------------------------------- /verl/tests/utils/test_flops_counter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/test_flops_counter.py -------------------------------------------------------------------------------- /verl/tests/utils/test_fs_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/test_fs_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/utils/test_import_utils_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/test_import_utils_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/utils/test_linear_cross_entropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/test_linear_cross_entropy.py -------------------------------------------------------------------------------- /verl/tests/utils/test_linear_cross_entropy_tp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/test_linear_cross_entropy_tp.py -------------------------------------------------------------------------------- /verl/tests/utils/test_model_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/test_model_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/utils/test_seqlen_balancing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/test_seqlen_balancing.py -------------------------------------------------------------------------------- /verl/tests/utils/test_timeout_decorator_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/test_timeout_decorator_cpu.py -------------------------------------------------------------------------------- /verl/tests/utils/test_torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/utils/test_torch_functional.py -------------------------------------------------------------------------------- /verl/tests/workers/reward_manager/test_registry_on_cpu.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/reward_manager/test_registry_on_cpu.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/async_rollout_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/async_rollout_utils.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/perf/vllm_async_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/perf/vllm_async_rollout.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/resource/tool_configs/sandbox_fusion_tool_config: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/resource/tool_configs/sandbox_fusion_tool_config -------------------------------------------------------------------------------- /verl/tests/workers/rollout/resource/tool_configs/search_tool_config: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/resource/tool_configs/search_tool_config -------------------------------------------------------------------------------- /verl/tests/workers/rollout/rollout_vllm/run_fsdp_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/rollout_vllm/run_fsdp_vllm.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/rollout_vllm/test_vllm_chat_scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/rollout_vllm/test_vllm_chat_scheduler.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/rollout_vllm/test_vllm_hf_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/rollout_vllm/test_vllm_hf_loader.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/rollout_vllm/test_vllm_spmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/rollout_vllm/test_vllm_spmd.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/test_async_sglang_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/test_async_sglang_server.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/test_custom_completion_callback.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/test_custom_completion_callback.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/test_hf_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/test_hf_rollout.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/test_sglang_async_rollout_search_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/test_sglang_async_rollout_search_tools.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/test_sglang_async_rollout_sf_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/test_sglang_async_rollout_sf_tools.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/test_sglang_async_rollout_w_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/test_sglang_async_rollout_w_tools.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/test_sglang_spmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/test_sglang_spmd.py -------------------------------------------------------------------------------- /verl/tests/workers/rollout/utils_sglang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/tests/workers/rollout/utils_sglang.py -------------------------------------------------------------------------------- /verl/verl/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/.DS_Store -------------------------------------------------------------------------------- /verl/verl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/README.md -------------------------------------------------------------------------------- /verl/verl/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/llama/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/llama/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/llama/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/checkpoint_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/llama/megatron/checkpoint_utils/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/checkpoint_utils/llama_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/llama/megatron/checkpoint_utils/llama_loader.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/checkpoint_utils/llama_loader_depracated.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/llama/megatron/checkpoint_utils/llama_loader_depracated.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/checkpoint_utils/llama_saver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/llama/megatron/checkpoint_utils/llama_saver.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/llama/megatron/layers/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/parallel_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/llama/megatron/layers/parallel_attention.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/parallel_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/llama/megatron/layers/parallel_decoder.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/parallel_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/llama/megatron/layers/parallel_linear.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/parallel_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/llama/megatron/layers/parallel_mlp.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/parallel_rmsnorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/llama/megatron/layers/parallel_rmsnorm.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/modeling_llama_megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/llama/megatron/modeling_llama_megatron.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/config_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/config_converter.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/loader.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/model_forward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/model_forward.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/model_initializer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/model_initializer.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/patch_v012.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/patch_v012.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/qwen2_5_vl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/qwen2_5_vl/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/qwen2_5_vl/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/qwen2_5_vl/attention.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/qwen2_5_vl/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/qwen2_5_vl/model.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/qwen2_5_vl/rope_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/qwen2_5_vl/rope_utils.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/qwen2_5_vl/vision_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/qwen2_5_vl/vision_config.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/qwen2_5_vl/vision_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/qwen2_5_vl/vision_model.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/qwen2_5_vl/vision_transformer_block.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/qwen2_5_vl/vision_transformer_block.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/readme.md -------------------------------------------------------------------------------- /verl/verl/models/mcore/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/registry.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/saver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/saver.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/util.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/weight_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/mcore/weight_converter.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/qwen2/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/qwen2/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/checkpoint_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/qwen2/megatron/checkpoint_utils/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader_depracated.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader_depracated.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/checkpoint_utils/qwen2_saver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/qwen2/megatron/checkpoint_utils/qwen2_saver.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/qwen2/megatron/layers/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/parallel_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/qwen2/megatron/layers/parallel_attention.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/parallel_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/qwen2/megatron/layers/parallel_decoder.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/parallel_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/qwen2/megatron/layers/parallel_linear.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/parallel_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/qwen2/megatron/layers/parallel_mlp.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/parallel_rmsnorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/qwen2/megatron/layers/parallel_rmsnorm.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/modeling_qwen2_megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/qwen2/megatron/modeling_qwen2_megatron.py -------------------------------------------------------------------------------- /verl/verl/models/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/registry.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/transformers/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/dense_common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/transformers/dense_common.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/kimi_vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/transformers/kimi_vl.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/transformers/llama.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/transformers/monkey_patch.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/qwen2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/transformers/qwen2.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/qwen2_5_vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/transformers/qwen2_5_vl.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/qwen2_vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/transformers/qwen2_vl.py -------------------------------------------------------------------------------- /verl/verl/models/weight_loader_registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/models/weight_loader_registry.py -------------------------------------------------------------------------------- /verl/verl/protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/protocol.py -------------------------------------------------------------------------------- /verl/verl/single_controller/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/single_controller/__init__.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/single_controller/base/__init__.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/single_controller/base/decorator.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/single_controller/base/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/megatron/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/single_controller/base/megatron/worker.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/megatron/worker_group.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/single_controller/base/megatron/worker_group.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/register_center/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/single_controller/base/register_center/__init__.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/register_center/ray.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/single_controller/base/register_center/ray.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/single_controller/base/worker.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/worker_group.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/single_controller/base/worker_group.py -------------------------------------------------------------------------------- /verl/verl/single_controller/ray/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/single_controller/ray/__init__.py -------------------------------------------------------------------------------- /verl/verl/single_controller/ray/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/single_controller/ray/base.py -------------------------------------------------------------------------------- /verl/verl/single_controller/ray/megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/single_controller/ray/megatron.py -------------------------------------------------------------------------------- /verl/verl/third_party/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/sglang/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/sglang/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/sglang/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/sglang/parallel_state.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/arg_utils.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/config.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/hf_weight_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/hf_weight_loader.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/llm.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/model_runner.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_5_4/worker.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/arg_utils.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/config.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/hf_weight_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/hf_weight_loader.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/llm.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/model_runner.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/tokenizer.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_6_3/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/worker.py -------------------------------------------------------------------------------- /verl/verl/tools/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/.DS_Store -------------------------------------------------------------------------------- /verl/verl/tools/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/__init__.py -------------------------------------------------------------------------------- /verl/verl/tools/base_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/base_tool.py -------------------------------------------------------------------------------- /verl/verl/tools/config/search_tool_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/config/search_tool_config.yaml -------------------------------------------------------------------------------- /verl/verl/tools/config/video_tool_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/config/video_tool_config.yaml -------------------------------------------------------------------------------- /verl/verl/tools/config/video_tool_config_1getframe.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/config/video_tool_config_1getframe.yaml -------------------------------------------------------------------------------- /verl/verl/tools/config/video_tool_config_2getcaption.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/config/video_tool_config_2getcaption.yaml -------------------------------------------------------------------------------- /verl/verl/tools/config/video_tool_config_3askquestion.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/config/video_tool_config_3askquestion.yaml -------------------------------------------------------------------------------- /verl/verl/tools/config/zoom_tool_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/config/zoom_tool_config.yaml -------------------------------------------------------------------------------- /verl/verl/tools/config/zoom_tool_config_2getcaption.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/config/zoom_tool_config_2getcaption.yaml -------------------------------------------------------------------------------- /verl/verl/tools/config/zoom_tool_config_3askquestion.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/config/zoom_tool_config_3askquestion.yaml -------------------------------------------------------------------------------- /verl/verl/tools/config/zoom_tool_config_new.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/config/zoom_tool_config_new.yaml -------------------------------------------------------------------------------- /verl/verl/tools/config/zoom_tool_config_new_all_for_paper.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/config/zoom_tool_config_new_all_for_paper.yaml -------------------------------------------------------------------------------- /verl/verl/tools/gsm8k_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/gsm8k_tool.py -------------------------------------------------------------------------------- /verl/verl/tools/sandbox_fusion_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/sandbox_fusion_tools.py -------------------------------------------------------------------------------- /verl/verl/tools/schemas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/schemas.py -------------------------------------------------------------------------------- /verl/verl/tools/search_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/search_tool.py -------------------------------------------------------------------------------- /verl/verl/tools/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/utils/__init__.py -------------------------------------------------------------------------------- /verl/verl/tools/utils/search_r1_like_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/utils/search_r1_like_utils.py -------------------------------------------------------------------------------- /verl/verl/tools/video_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/video_tools.py -------------------------------------------------------------------------------- /verl/verl/tools/zoom_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/zoom_tool.py -------------------------------------------------------------------------------- /verl/verl/tools/zoom_tool_new.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/tools/zoom_tool_new.py -------------------------------------------------------------------------------- /verl/verl/trainer/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/.DS_Store -------------------------------------------------------------------------------- /verl/verl/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/__init__.py -------------------------------------------------------------------------------- /verl/verl/trainer/config/evaluation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/config/evaluation.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/config/generation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/config/generation.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/config/ppo_megatron_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/config/ppo_megatron_trainer.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/config/ppo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/config/ppo_trainer.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/config/sft_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/config/sft_trainer.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/fsdp_sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/fsdp_sft_trainer.py -------------------------------------------------------------------------------- /verl/verl/trainer/main_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/main_eval.py -------------------------------------------------------------------------------- /verl/verl/trainer/main_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/main_generation.py -------------------------------------------------------------------------------- /verl/verl/trainer/main_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/main_ppo.py -------------------------------------------------------------------------------- /verl/verl/trainer/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/ppo/__init__.py -------------------------------------------------------------------------------- /verl/verl/trainer/ppo/core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/ppo/core_algos.py -------------------------------------------------------------------------------- /verl/verl/trainer/ppo/metric_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/ppo/metric_utils.py -------------------------------------------------------------------------------- /verl/verl/trainer/ppo/ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/ppo/ray_trainer.py -------------------------------------------------------------------------------- /verl/verl/trainer/ppo/reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/ppo/reward.py -------------------------------------------------------------------------------- /verl/verl/trainer/runtime_env.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/trainer/runtime_env.yaml -------------------------------------------------------------------------------- /verl/verl/utils/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/.DS_Store -------------------------------------------------------------------------------- /verl/verl/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/activation_offload.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/activation_offload.py -------------------------------------------------------------------------------- /verl/verl/utils/checkpoint/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/checkpoint/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/checkpoint/checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/checkpoint/checkpoint_manager.py -------------------------------------------------------------------------------- /verl/verl/utils/checkpoint/fsdp_checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/checkpoint/fsdp_checkpoint_manager.py -------------------------------------------------------------------------------- /verl/verl/utils/checkpoint/megatron_checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/checkpoint/megatron_checkpoint_manager.py -------------------------------------------------------------------------------- /verl/verl/utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/config.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/DejaVuSans-Bold.ttf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/dataset/DejaVuSans-Bold.ttf -------------------------------------------------------------------------------- /verl/verl/utils/dataset/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/dataset/README.md -------------------------------------------------------------------------------- /verl/verl/utils/dataset/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/dataset/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/multiturn_sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/dataset/multiturn_sft_dataset.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/rl_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/dataset/rl_dataset.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/rl_dataset_multi_turn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/dataset/rl_dataset_multi_turn.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/rl_sampler_multimodal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/dataset/rl_sampler_multimodal.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/rm_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/dataset/rm_dataset.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/dataset/sampler.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/dataset/sft_dataset.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/sft_dataset_multi_turn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/dataset/sft_dataset_multi_turn.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/video_vl_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/dataset/video_vl_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/vision_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/dataset/vision_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/debug/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/debug/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/debug/performance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/debug/performance.py -------------------------------------------------------------------------------- /verl/verl/utils/debug/profile.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/debug/profile.py -------------------------------------------------------------------------------- /verl/verl/utils/debug/trajectory_tracker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/debug/trajectory_tracker.py -------------------------------------------------------------------------------- /verl/verl/utils/device.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/device.py -------------------------------------------------------------------------------- /verl/verl/utils/distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/distributed.py -------------------------------------------------------------------------------- /verl/verl/utils/experimental/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/experimental/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/experimental/torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/experimental/torch_functional.py -------------------------------------------------------------------------------- /verl/verl/utils/flops_counter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/flops_counter.py -------------------------------------------------------------------------------- /verl/verl/utils/fs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/fs.py -------------------------------------------------------------------------------- /verl/verl/utils/fsdp_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/fsdp_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/hdfs_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/hdfs_io.py -------------------------------------------------------------------------------- /verl/verl/utils/import_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/import_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/kernel/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/kernel/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/kernel/kernels.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/kernel/kernels.py -------------------------------------------------------------------------------- /verl/verl/utils/kernel/linear_cross_entropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/kernel/linear_cross_entropy.py -------------------------------------------------------------------------------- /verl/verl/utils/logger/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/logger/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/logger/aggregate_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/logger/aggregate_logger.py -------------------------------------------------------------------------------- /verl/verl/utils/logging_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/logging_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/megatron/memory.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/megatron/optimizer.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/pipeline_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/megatron/pipeline_parallel.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/sequence_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/megatron/sequence_parallel.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/tensor_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/megatron/tensor_parallel.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/megatron_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/memory_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/memory_buffer.py -------------------------------------------------------------------------------- /verl/verl/utils/metric/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/metric/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/metric/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/metric/utils.py -------------------------------------------------------------------------------- /verl/verl/utils/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/model.py -------------------------------------------------------------------------------- /verl/verl/utils/net_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/net_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/py_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/py_functional.py -------------------------------------------------------------------------------- /verl/verl/utils/ray_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/ray_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/rendezvous/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/rendezvous/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/rendezvous/ray_backend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/rendezvous/ray_backend.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/.DS_Store -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/charades.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/charades.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/charades_cutreward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/charades_cutreward.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/geo3k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/geo3k.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/gqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/gqa.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/gqa_cutreward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/gqa_cutreward.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/gsm8k.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/math.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/math_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/math_batch.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/math_dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/math_dapo.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/math_verify.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/math_verify.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_code/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/prime_code/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_code/testing_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/prime_code/testing_util.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_code/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/prime_code/utils.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_math/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/prime_math/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_math/grader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/prime_math/grader.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_math/math_normalize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/prime_math/math_normalize.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/sandbox_fusion/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/sandbox_fusion/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/sandbox_fusion/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/sandbox_fusion/utils.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/search_r1_like_qa_em.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/search_r1_like_qa_em.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/vidchapter_cutreward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/vidchapter_cutreward.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/video_r1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/reward_score/video_r1.py -------------------------------------------------------------------------------- /verl/verl/utils/seqlen_balancing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/seqlen_balancing.py -------------------------------------------------------------------------------- /verl/verl/utils/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/tokenizer.py -------------------------------------------------------------------------------- /verl/verl/utils/torch_dtypes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/torch_dtypes.py -------------------------------------------------------------------------------- /verl/verl/utils/torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/torch_functional.py -------------------------------------------------------------------------------- /verl/verl/utils/tracking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/tracking.py -------------------------------------------------------------------------------- /verl/verl/utils/ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/ulysses.py -------------------------------------------------------------------------------- /verl/verl/utils/vllm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/utils/vllm_utils.py -------------------------------------------------------------------------------- /verl/verl/version/version: -------------------------------------------------------------------------------- 1 | 0.4.0.dev 2 | -------------------------------------------------------------------------------- /verl/verl/workers/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/.DS_Store -------------------------------------------------------------------------------- /verl/verl/workers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/actor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/actor/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/actor/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/actor/base.py -------------------------------------------------------------------------------- /verl/verl/workers/actor/dp_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/actor/dp_actor.py -------------------------------------------------------------------------------- /verl/verl/workers/actor/megatron_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/actor/megatron_actor.py -------------------------------------------------------------------------------- /verl/verl/workers/critic/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/critic/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/critic/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/critic/base.py -------------------------------------------------------------------------------- /verl/verl/workers/critic/dp_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/critic/dp_critic.py -------------------------------------------------------------------------------- /verl/verl/workers/critic/megatron_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/critic/megatron_critic.py -------------------------------------------------------------------------------- /verl/verl/workers/fsdp_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/fsdp_workers.py -------------------------------------------------------------------------------- /verl/verl/workers/megatron_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/megatron_workers.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/reward_manager/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/reward_manager/batch.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/reward_manager/dapo.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/reward_manager/naive.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/naive_multiturn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/reward_manager/naive_multiturn.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/prime.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/reward_manager/prime.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/prime_multiturn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/reward_manager/prime_multiturn.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/reward_manager/registry.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/reward_model/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_model/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/reward_model/base.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_model/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/reward_model/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_model/megatron/reward_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/reward_model/megatron/reward_model.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/.DS_Store -------------------------------------------------------------------------------- /verl/verl/workers/rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/async_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/async_server.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/base.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/chat_scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/chat_scheduler.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/hf_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/hf_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/naive/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/naive/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/naive/naive_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/naive/naive_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/schemas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/schemas.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/sglang_rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/sglang_rollout/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/sglang_rollout/async_sglang_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/sglang_rollout/async_sglang_server.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/sglang_rollout/sglang_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/sglang_rollout/sglang_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/sglang_rollout/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/sglang_rollout/utils.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/tokenizer.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/vllm_rollout/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/fire_vllm_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/vllm_rollout/fire_vllm_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/vllm_async_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/vllm_rollout/vllm_async_server.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/vllm_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/vllm_rollout/vllm_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd_multi_turn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd_multi_turn.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd_multi_turn_sync.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd_multi_turn_sync.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/sharding_manager/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/sharding_manager/base.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/fsdp_sglang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/sharding_manager/fsdp_sglang.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/fsdp_ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/sharding_manager/fsdp_ulysses.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/fsdp_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/sharding_manager/fsdp_vllm.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/megatron_sglang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/sharding_manager/megatron_sglang.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/megatron_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/zhang9302002/ThinkingWithVideos/HEAD/verl/verl/workers/sharding_manager/megatron_vllm.py --------------------------------------------------------------------------------