├── README.md ├── assets ├── Figure1.png └── Figure2.jpg └── verl ├── .gitignore ├── .pre-commit-config.yaml ├── .readthedocs.yaml ├── LICENSE ├── Notice.txt ├── data ├── AIME-TTT │ ├── test.json │ ├── train-simplerl-16.parquet │ └── train.json ├── AIME25 │ ├── test.json │ └── train.json ├── AMC-TTT │ ├── test.json │ └── train.json ├── GPQA-TTT │ ├── test.json │ └── train.json ├── MATH-TTT │ ├── math_train_ttrl.parquet │ ├── test.json │ └── train.json └── preprocess_simplerl.py ├── deploy_vllm_embedding.sh ├── docker ├── Dockerfile.megatron ├── Dockerfile.ngc.vllm ├── Dockerfile.ngc.vllm0.8 ├── Dockerfile.ngc.vllm0.8.sagemaker ├── Dockerfile.rocm ├── Dockerfile.sglang └── Dockerfile.vemlp.vllm.te ├── docs ├── Makefile ├── README.md ├── README_vllm0.7.md ├── README_vllm0.8.md ├── _static │ └── logo.png ├── advance │ ├── checkpoint.rst │ ├── dpo_extension.rst │ ├── fsdp_extension.rst │ ├── megatron_extension.rst │ └── placement.rst ├── amd_tutorial │ └── amd_build_dockerfile_page.rst ├── conf.py ├── data.rst ├── examples │ ├── config.rst │ ├── gsm8k_example.rst │ └── ppo_code_architecture.rst ├── experiment │ └── ppo.rst ├── faq │ └── faq.rst ├── hybrid_flow.rst ├── index.rst ├── perf │ ├── device_tuning.rst │ └── perf_tuning.rst ├── preparation │ ├── prepare_data.rst │ └── reward_function.rst ├── requirements-docs.txt ├── start │ ├── install.rst │ ├── multinode.rst │ └── quickstart.rst └── workers │ ├── fsdp_workers.rst │ ├── megatron_workers.rst │ ├── ray_trainer.rst │ └── sglang_worker.rst ├── examples └── labelfree │ ├── evol_rl.sh │ └── ttrl_baseline.sh ├── fast_eval_metrics.py ├── patches └── megatron_v4.patch ├── pyproject.toml ├── recipe ├── dapo │ ├── README.md │ ├── prepare_dapo_data.sh │ ├── run_dapo_early_qwen2.5_32b.sh │ ├── run_dapo_qwen2.5_32b.sh │ ├── src │ │ ├── config │ │ │ └── dapo_trainer.yaml │ │ ├── dapo_ray_trainer.py │ │ └── main_dapo.py │ └── test_dapo_7b.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 │ ├── ttrl_math_prime_1.5b.sh │ └── ttrl_math_prime_1.5b_dsw.sh └── r1 │ ├── README.md │ ├── __init__.py │ ├── config │ └── evaluation.yaml │ ├── data_process.py │ ├── main_eval.py │ ├── reward_score.py │ ├── run_r1_aime.sh │ ├── run_r1_distill_qwen.sh │ └── tasks │ ├── __init__.py │ ├── gpqa.py │ ├── livecodebench.py │ └── math.py ├── requirements.txt ├── requirements_sglang.txt ├── scripts ├── converter_hf_to_mcore.py ├── diagnose.py ├── generate_rollouts_and_embed.py ├── model_merger.py └── plot_embedding_tsne.py ├── setup.py ├── test_three_datasets.sh ├── tests ├── __init__.py ├── checkpoint │ └── test_fsdp_ckpt.py ├── distributed │ ├── run_all.sh │ └── test_tensor_dict.py ├── e2e │ ├── __init__.py │ ├── arithmetic_sequence │ │ ├── data │ │ │ └── create_dataset.py │ │ ├── model │ │ │ ├── config.json │ │ │ ├── create_model_tokenizer.py │ │ │ ├── generation_config.json │ │ │ ├── model.safetensors │ │ │ └── tokenizer_config.json │ │ └── rl │ │ │ ├── README.md │ │ │ └── main_trainer.py │ ├── check_custom_rwd_fn.py │ ├── check_results.py │ ├── envs │ │ ├── __init__.py │ │ └── digit_completion │ │ │ ├── __init__.py │ │ │ ├── task.py │ │ │ └── tokenizer.py │ ├── ppo_trainer │ │ ├── run_function_reward.sh │ │ └── run_model_reward.sh │ ├── run_dapo.sh │ ├── run_ppo_trainer_megatron.sh │ ├── run_prime.sh │ ├── run_r1_distill_qwen_aime24_eval.sh │ ├── run_ray_trainer.sh │ ├── run_ray_trainer_fire_sampling.sh │ ├── run_ray_trainer_rmpad.sh │ ├── run_test.sh │ └── sft │ │ ├── run_sft.sh │ │ └── test_sp_loss_match.py ├── generation │ └── run_gen_qwen05.sh ├── gpu_utility │ ├── test_memory_buffers.py │ ├── test_ops.py │ └── test_torch_functional.py ├── kill_github_tests.sh ├── model │ ├── test_transformer.py │ └── test_transformers_ulysses.py ├── ray │ ├── check_worker_alive │ │ └── main.py │ ├── detached_worker │ │ ├── README.md │ │ ├── client.py │ │ ├── run.sh │ │ └── server.py │ ├── test_check_worker_alive.py │ ├── test_colocated_workers.py │ ├── test_data_transfer.py │ ├── test_driverfunc_to_worker.py │ ├── test_high_level_scheduling_api.py │ ├── test_ray_local_envs.py │ ├── test_rvdz.py │ ├── test_worker_group_basics.py │ └── test_worker_group_torch.py ├── rollout │ ├── run_fsdp_vllm.py │ ├── test_sglang_spmd.py │ ├── test_vllm_hf_loader.py │ └── test_vllm_spmd.py ├── sandbox │ └── test_sandbox.py ├── sanity │ ├── check_license.py │ └── test_import.py ├── utility │ └── test_tensor_dict_utilities.py └── verl │ └── utils │ ├── dataset │ ├── test_multiturn_sft_dataset.py │ ├── test_rl_dataset.py │ ├── test_rm_dataset.py │ └── test_sft_dataset.py │ ├── test_import_utils.py │ └── test_module.py ├── verl ├── __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 │ │ ├── readme.md │ │ ├── registry.py │ │ ├── saver.py │ │ └── util.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 │ │ ├── llama.py │ │ ├── monkey_patch.py │ │ ├── qwen2.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_3_1 │ │ ├── __init__.py │ │ ├── arg_utils.py │ │ ├── config.py │ │ ├── llm.py │ │ ├── llm_engine_sp.py │ │ ├── model_loader.py │ │ ├── model_runner.py │ │ ├── parallel_state.py │ │ ├── tokenizer.py │ │ ├── weight_loaders.py │ │ └── worker.py │ │ ├── vllm_v_0_4_2 │ │ ├── __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_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 ├── trainer │ ├── __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 │ └── runtime_env.yaml ├── utils │ ├── __init__.py │ ├── checkpoint │ │ ├── __init__.py │ │ ├── checkpoint_manager.py │ │ ├── fsdp_checkpoint_manager.py │ │ └── megatron_checkpoint_manager.py │ ├── config.py │ ├── dataset │ │ ├── README.md │ │ ├── __init__.py │ │ ├── multiturn_sft_dataset.py │ │ ├── rl_dataset.py │ │ ├── rm_dataset.py │ │ ├── sft_dataset.py │ │ └── vision_utils.py │ ├── debug │ │ ├── __init__.py │ │ ├── performance.py │ │ └── trajectory_tracker.py │ ├── distributed.py │ ├── flops_counter.py │ ├── fs.py │ ├── fsdp_utils.py │ ├── hdfs_io.py │ ├── import_utils.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 │ ├── model.py │ ├── py_functional.py │ ├── ray_utils.py │ ├── rendezvous │ │ ├── __init__.py │ │ └── ray_backend.py │ ├── reward_score │ │ ├── __init__.py │ │ ├── geo3k.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 │ │ └── ttrl │ │ │ ├── auto_extract.py │ │ │ ├── auto_verify.py │ │ │ ├── latex_clean.py │ │ │ ├── qwen │ │ │ ├── grader.py │ │ │ ├── math_grade.py │ │ │ ├── math_normalize.py │ │ │ ├── qwen_eval.py │ │ │ ├── qwen_math_parser.py │ │ │ └── simplerl_math_equal.py │ │ │ └── ttt_metrics.py │ ├── seqlen_balancing.py │ ├── tokenizer.py │ ├── torch_dtypes.py │ ├── torch_functional.py │ ├── tracking.py │ └── ulysses.py ├── version │ └── version └── workers │ ├── __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 │ ├── prime.py │ ├── semantic_novelty.py │ └── ttrl.py │ ├── reward_model │ ├── __init__.py │ ├── base.py │ └── megatron │ │ ├── __init__.py │ │ └── reward_model.py │ ├── rollout │ ├── __init__.py │ ├── base.py │ ├── hf_rollout.py │ ├── naive │ │ ├── __init__.py │ │ └── naive_rollout.py │ ├── sglang_rollout │ │ ├── __init__.py │ │ └── sglang_rollout.py │ ├── tokenizer.py │ └── vllm_rollout │ │ ├── __init__.py │ │ ├── fire_vllm_rollout.py │ │ ├── vllm_rollout.py │ │ └── vllm_rollout_spmd.py │ └── sharding_manager │ ├── __init__.py │ ├── base.py │ ├── fsdp_sglang.py │ ├── fsdp_ulysses.py │ ├── fsdp_vllm.py │ ├── megatron_vllm.py │ └── patch │ ├── __init__.py │ └── fsdp_vllm_patch.py └── vllm_embedding_api.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/README.md -------------------------------------------------------------------------------- /assets/Figure1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/assets/Figure1.png -------------------------------------------------------------------------------- /assets/Figure2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/assets/Figure2.jpg -------------------------------------------------------------------------------- /verl/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/.gitignore -------------------------------------------------------------------------------- /verl/.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/.pre-commit-config.yaml -------------------------------------------------------------------------------- /verl/.readthedocs.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/.readthedocs.yaml -------------------------------------------------------------------------------- /verl/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/LICENSE -------------------------------------------------------------------------------- /verl/Notice.txt: -------------------------------------------------------------------------------- 1 | Copyright 2023-2024 Bytedance Ltd. and/or its affiliates -------------------------------------------------------------------------------- /verl/data/AIME-TTT/test.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/data/AIME-TTT/test.json -------------------------------------------------------------------------------- /verl/data/AIME-TTT/train-simplerl-16.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/data/AIME-TTT/train-simplerl-16.parquet -------------------------------------------------------------------------------- /verl/data/AIME-TTT/train.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/data/AIME-TTT/train.json -------------------------------------------------------------------------------- /verl/data/AIME25/test.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/data/AIME25/test.json -------------------------------------------------------------------------------- /verl/data/AIME25/train.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/data/AIME25/train.json -------------------------------------------------------------------------------- /verl/data/AMC-TTT/test.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/data/AMC-TTT/test.json -------------------------------------------------------------------------------- /verl/data/AMC-TTT/train.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/data/AMC-TTT/train.json -------------------------------------------------------------------------------- /verl/data/GPQA-TTT/test.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/data/GPQA-TTT/test.json -------------------------------------------------------------------------------- /verl/data/GPQA-TTT/train.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/data/GPQA-TTT/train.json -------------------------------------------------------------------------------- /verl/data/MATH-TTT/math_train_ttrl.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/data/MATH-TTT/math_train_ttrl.parquet -------------------------------------------------------------------------------- /verl/data/MATH-TTT/test.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/data/MATH-TTT/test.json -------------------------------------------------------------------------------- /verl/data/MATH-TTT/train.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/data/MATH-TTT/train.json -------------------------------------------------------------------------------- /verl/data/preprocess_simplerl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/data/preprocess_simplerl.py -------------------------------------------------------------------------------- /verl/deploy_vllm_embedding.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/deploy_vllm_embedding.sh -------------------------------------------------------------------------------- /verl/docker/Dockerfile.megatron: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docker/Dockerfile.megatron -------------------------------------------------------------------------------- /verl/docker/Dockerfile.ngc.vllm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docker/Dockerfile.ngc.vllm -------------------------------------------------------------------------------- /verl/docker/Dockerfile.ngc.vllm0.8: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docker/Dockerfile.ngc.vllm0.8 -------------------------------------------------------------------------------- /verl/docker/Dockerfile.ngc.vllm0.8.sagemaker: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docker/Dockerfile.ngc.vllm0.8.sagemaker -------------------------------------------------------------------------------- /verl/docker/Dockerfile.rocm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docker/Dockerfile.rocm -------------------------------------------------------------------------------- /verl/docker/Dockerfile.sglang: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docker/Dockerfile.sglang -------------------------------------------------------------------------------- /verl/docker/Dockerfile.vemlp.vllm.te: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docker/Dockerfile.vemlp.vllm.te -------------------------------------------------------------------------------- /verl/docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/Makefile -------------------------------------------------------------------------------- /verl/docs/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/README.md -------------------------------------------------------------------------------- /verl/docs/README_vllm0.7.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/README_vllm0.7.md -------------------------------------------------------------------------------- /verl/docs/README_vllm0.8.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/README_vllm0.8.md -------------------------------------------------------------------------------- /verl/docs/_static/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/_static/logo.png -------------------------------------------------------------------------------- /verl/docs/advance/checkpoint.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/advance/checkpoint.rst -------------------------------------------------------------------------------- /verl/docs/advance/dpo_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/advance/dpo_extension.rst -------------------------------------------------------------------------------- /verl/docs/advance/fsdp_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/advance/fsdp_extension.rst -------------------------------------------------------------------------------- /verl/docs/advance/megatron_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/advance/megatron_extension.rst -------------------------------------------------------------------------------- /verl/docs/advance/placement.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/advance/placement.rst -------------------------------------------------------------------------------- /verl/docs/amd_tutorial/amd_build_dockerfile_page.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/amd_tutorial/amd_build_dockerfile_page.rst -------------------------------------------------------------------------------- /verl/docs/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/conf.py -------------------------------------------------------------------------------- /verl/docs/data.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/data.rst -------------------------------------------------------------------------------- /verl/docs/examples/config.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/examples/config.rst -------------------------------------------------------------------------------- /verl/docs/examples/gsm8k_example.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/examples/gsm8k_example.rst -------------------------------------------------------------------------------- /verl/docs/examples/ppo_code_architecture.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/examples/ppo_code_architecture.rst -------------------------------------------------------------------------------- /verl/docs/experiment/ppo.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/experiment/ppo.rst -------------------------------------------------------------------------------- /verl/docs/faq/faq.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/faq/faq.rst -------------------------------------------------------------------------------- /verl/docs/hybrid_flow.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/hybrid_flow.rst -------------------------------------------------------------------------------- /verl/docs/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/index.rst -------------------------------------------------------------------------------- /verl/docs/perf/device_tuning.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/perf/device_tuning.rst -------------------------------------------------------------------------------- /verl/docs/perf/perf_tuning.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/perf/perf_tuning.rst -------------------------------------------------------------------------------- /verl/docs/preparation/prepare_data.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/preparation/prepare_data.rst -------------------------------------------------------------------------------- /verl/docs/preparation/reward_function.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/preparation/reward_function.rst -------------------------------------------------------------------------------- /verl/docs/requirements-docs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/requirements-docs.txt -------------------------------------------------------------------------------- /verl/docs/start/install.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/start/install.rst -------------------------------------------------------------------------------- /verl/docs/start/multinode.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/start/multinode.rst -------------------------------------------------------------------------------- /verl/docs/start/quickstart.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/start/quickstart.rst -------------------------------------------------------------------------------- /verl/docs/workers/fsdp_workers.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/workers/fsdp_workers.rst -------------------------------------------------------------------------------- /verl/docs/workers/megatron_workers.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/workers/megatron_workers.rst -------------------------------------------------------------------------------- /verl/docs/workers/ray_trainer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/workers/ray_trainer.rst -------------------------------------------------------------------------------- /verl/docs/workers/sglang_worker.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/docs/workers/sglang_worker.rst -------------------------------------------------------------------------------- /verl/examples/labelfree/evol_rl.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/examples/labelfree/evol_rl.sh -------------------------------------------------------------------------------- /verl/examples/labelfree/ttrl_baseline.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/examples/labelfree/ttrl_baseline.sh -------------------------------------------------------------------------------- /verl/fast_eval_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/fast_eval_metrics.py -------------------------------------------------------------------------------- /verl/patches/megatron_v4.patch: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/patches/megatron_v4.patch -------------------------------------------------------------------------------- /verl/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/pyproject.toml -------------------------------------------------------------------------------- /verl/recipe/dapo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/dapo/README.md -------------------------------------------------------------------------------- /verl/recipe/dapo/prepare_dapo_data.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/dapo/prepare_dapo_data.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/run_dapo_early_qwen2.5_32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/dapo/run_dapo_early_qwen2.5_32b.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/run_dapo_qwen2.5_32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/dapo/run_dapo_qwen2.5_32b.sh -------------------------------------------------------------------------------- /verl/recipe/dapo/src/config/dapo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/dapo/src/config/dapo_trainer.yaml -------------------------------------------------------------------------------- /verl/recipe/dapo/src/dapo_ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/dapo/src/dapo_ray_trainer.py -------------------------------------------------------------------------------- /verl/recipe/dapo/src/main_dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/dapo/src/main_dapo.py -------------------------------------------------------------------------------- /verl/recipe/dapo/test_dapo_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/dapo/test_dapo_7b.sh -------------------------------------------------------------------------------- /verl/recipe/prime/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/prime/__init__.py -------------------------------------------------------------------------------- /verl/recipe/prime/config/prime_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/prime/config/prime_trainer.yaml -------------------------------------------------------------------------------- /verl/recipe/prime/main_prime.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/prime/main_prime.py -------------------------------------------------------------------------------- /verl/recipe/prime/prime_core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/prime/prime_core_algos.py -------------------------------------------------------------------------------- /verl/recipe/prime/prime_dp_rm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/prime/prime_dp_rm.py -------------------------------------------------------------------------------- /verl/recipe/prime/prime_fsdp_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/prime/prime_fsdp_workers.py -------------------------------------------------------------------------------- /verl/recipe/prime/prime_ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/prime/prime_ray_trainer.py -------------------------------------------------------------------------------- /verl/recipe/prime/run_prime_qwen.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/prime/run_prime_qwen.sh -------------------------------------------------------------------------------- /verl/recipe/prime/ttrl_math_prime_1.5b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/prime/ttrl_math_prime_1.5b.sh -------------------------------------------------------------------------------- /verl/recipe/prime/ttrl_math_prime_1.5b_dsw.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/prime/ttrl_math_prime_1.5b_dsw.sh -------------------------------------------------------------------------------- /verl/recipe/r1/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/r1/README.md -------------------------------------------------------------------------------- /verl/recipe/r1/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/r1/__init__.py -------------------------------------------------------------------------------- /verl/recipe/r1/config/evaluation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/r1/config/evaluation.yaml -------------------------------------------------------------------------------- /verl/recipe/r1/data_process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/r1/data_process.py -------------------------------------------------------------------------------- /verl/recipe/r1/main_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/r1/main_eval.py -------------------------------------------------------------------------------- /verl/recipe/r1/reward_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/r1/reward_score.py -------------------------------------------------------------------------------- /verl/recipe/r1/run_r1_aime.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/r1/run_r1_aime.sh -------------------------------------------------------------------------------- /verl/recipe/r1/run_r1_distill_qwen.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/r1/run_r1_distill_qwen.sh -------------------------------------------------------------------------------- /verl/recipe/r1/tasks/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/r1/tasks/__init__.py -------------------------------------------------------------------------------- /verl/recipe/r1/tasks/gpqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/r1/tasks/gpqa.py -------------------------------------------------------------------------------- /verl/recipe/r1/tasks/livecodebench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/r1/tasks/livecodebench.py -------------------------------------------------------------------------------- /verl/recipe/r1/tasks/math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/recipe/r1/tasks/math.py -------------------------------------------------------------------------------- /verl/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/requirements.txt -------------------------------------------------------------------------------- /verl/requirements_sglang.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/requirements_sglang.txt -------------------------------------------------------------------------------- /verl/scripts/converter_hf_to_mcore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/scripts/converter_hf_to_mcore.py -------------------------------------------------------------------------------- /verl/scripts/diagnose.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/scripts/diagnose.py -------------------------------------------------------------------------------- /verl/scripts/generate_rollouts_and_embed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/scripts/generate_rollouts_and_embed.py -------------------------------------------------------------------------------- /verl/scripts/model_merger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/scripts/model_merger.py -------------------------------------------------------------------------------- /verl/scripts/plot_embedding_tsne.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/scripts/plot_embedding_tsne.py -------------------------------------------------------------------------------- /verl/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/setup.py -------------------------------------------------------------------------------- /verl/test_three_datasets.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/test_three_datasets.sh -------------------------------------------------------------------------------- /verl/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/__init__.py -------------------------------------------------------------------------------- /verl/tests/checkpoint/test_fsdp_ckpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/checkpoint/test_fsdp_ckpt.py -------------------------------------------------------------------------------- /verl/tests/distributed/run_all.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/distributed/run_all.sh -------------------------------------------------------------------------------- /verl/tests/distributed/test_tensor_dict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/distributed/test_tensor_dict.py -------------------------------------------------------------------------------- /verl/tests/e2e/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/__init__.py -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/data/create_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/arithmetic_sequence/data/create_dataset.py -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/model/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/arithmetic_sequence/model/config.json -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/model/create_model_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/arithmetic_sequence/model/create_model_tokenizer.py -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/model/generation_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/arithmetic_sequence/model/generation_config.json -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/model/model.safetensors: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/arithmetic_sequence/model/model.safetensors -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/model/tokenizer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/arithmetic_sequence/model/tokenizer_config.json -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/rl/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/arithmetic_sequence/rl/README.md -------------------------------------------------------------------------------- /verl/tests/e2e/arithmetic_sequence/rl/main_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/arithmetic_sequence/rl/main_trainer.py -------------------------------------------------------------------------------- /verl/tests/e2e/check_custom_rwd_fn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/check_custom_rwd_fn.py -------------------------------------------------------------------------------- /verl/tests/e2e/check_results.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/check_results.py -------------------------------------------------------------------------------- /verl/tests/e2e/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/envs/__init__.py -------------------------------------------------------------------------------- /verl/tests/e2e/envs/digit_completion/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/envs/digit_completion/__init__.py -------------------------------------------------------------------------------- /verl/tests/e2e/envs/digit_completion/task.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/envs/digit_completion/task.py -------------------------------------------------------------------------------- /verl/tests/e2e/envs/digit_completion/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/envs/digit_completion/tokenizer.py -------------------------------------------------------------------------------- /verl/tests/e2e/ppo_trainer/run_function_reward.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/ppo_trainer/run_function_reward.sh -------------------------------------------------------------------------------- /verl/tests/e2e/ppo_trainer/run_model_reward.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/ppo_trainer/run_model_reward.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_dapo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/run_dapo.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_ppo_trainer_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/run_ppo_trainer_megatron.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_prime.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/run_prime.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_r1_distill_qwen_aime24_eval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/run_r1_distill_qwen_aime24_eval.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_ray_trainer.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/run_ray_trainer.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_ray_trainer_fire_sampling.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/run_ray_trainer_fire_sampling.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_ray_trainer_rmpad.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/run_ray_trainer_rmpad.sh -------------------------------------------------------------------------------- /verl/tests/e2e/run_test.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/run_test.sh -------------------------------------------------------------------------------- /verl/tests/e2e/sft/run_sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/sft/run_sft.sh -------------------------------------------------------------------------------- /verl/tests/e2e/sft/test_sp_loss_match.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/e2e/sft/test_sp_loss_match.py -------------------------------------------------------------------------------- /verl/tests/generation/run_gen_qwen05.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/generation/run_gen_qwen05.sh -------------------------------------------------------------------------------- /verl/tests/gpu_utility/test_memory_buffers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/gpu_utility/test_memory_buffers.py -------------------------------------------------------------------------------- /verl/tests/gpu_utility/test_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/gpu_utility/test_ops.py -------------------------------------------------------------------------------- /verl/tests/gpu_utility/test_torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/gpu_utility/test_torch_functional.py -------------------------------------------------------------------------------- /verl/tests/kill_github_tests.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/kill_github_tests.sh -------------------------------------------------------------------------------- /verl/tests/model/test_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/model/test_transformer.py -------------------------------------------------------------------------------- /verl/tests/model/test_transformers_ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/model/test_transformers_ulysses.py -------------------------------------------------------------------------------- /verl/tests/ray/check_worker_alive/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/ray/check_worker_alive/main.py -------------------------------------------------------------------------------- /verl/tests/ray/detached_worker/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/ray/detached_worker/README.md -------------------------------------------------------------------------------- /verl/tests/ray/detached_worker/client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/ray/detached_worker/client.py -------------------------------------------------------------------------------- /verl/tests/ray/detached_worker/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/ray/detached_worker/run.sh -------------------------------------------------------------------------------- /verl/tests/ray/detached_worker/server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/ray/detached_worker/server.py -------------------------------------------------------------------------------- /verl/tests/ray/test_check_worker_alive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/ray/test_check_worker_alive.py -------------------------------------------------------------------------------- /verl/tests/ray/test_colocated_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/ray/test_colocated_workers.py -------------------------------------------------------------------------------- /verl/tests/ray/test_data_transfer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/ray/test_data_transfer.py -------------------------------------------------------------------------------- /verl/tests/ray/test_driverfunc_to_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/ray/test_driverfunc_to_worker.py -------------------------------------------------------------------------------- /verl/tests/ray/test_high_level_scheduling_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/ray/test_high_level_scheduling_api.py -------------------------------------------------------------------------------- /verl/tests/ray/test_ray_local_envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/ray/test_ray_local_envs.py -------------------------------------------------------------------------------- /verl/tests/ray/test_rvdz.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/ray/test_rvdz.py -------------------------------------------------------------------------------- /verl/tests/ray/test_worker_group_basics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/ray/test_worker_group_basics.py -------------------------------------------------------------------------------- /verl/tests/ray/test_worker_group_torch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/ray/test_worker_group_torch.py -------------------------------------------------------------------------------- /verl/tests/rollout/run_fsdp_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/rollout/run_fsdp_vllm.py -------------------------------------------------------------------------------- /verl/tests/rollout/test_sglang_spmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/rollout/test_sglang_spmd.py -------------------------------------------------------------------------------- /verl/tests/rollout/test_vllm_hf_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/rollout/test_vllm_hf_loader.py -------------------------------------------------------------------------------- /verl/tests/rollout/test_vllm_spmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/rollout/test_vllm_spmd.py -------------------------------------------------------------------------------- /verl/tests/sandbox/test_sandbox.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/sandbox/test_sandbox.py -------------------------------------------------------------------------------- /verl/tests/sanity/check_license.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/sanity/check_license.py -------------------------------------------------------------------------------- /verl/tests/sanity/test_import.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/sanity/test_import.py -------------------------------------------------------------------------------- /verl/tests/utility/test_tensor_dict_utilities.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/utility/test_tensor_dict_utilities.py -------------------------------------------------------------------------------- /verl/tests/verl/utils/dataset/test_multiturn_sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/verl/utils/dataset/test_multiturn_sft_dataset.py -------------------------------------------------------------------------------- /verl/tests/verl/utils/dataset/test_rl_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/verl/utils/dataset/test_rl_dataset.py -------------------------------------------------------------------------------- /verl/tests/verl/utils/dataset/test_rm_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/verl/utils/dataset/test_rm_dataset.py -------------------------------------------------------------------------------- /verl/tests/verl/utils/dataset/test_sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/verl/utils/dataset/test_sft_dataset.py -------------------------------------------------------------------------------- /verl/tests/verl/utils/test_import_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/verl/utils/test_import_utils.py -------------------------------------------------------------------------------- /verl/tests/verl/utils/test_module.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/tests/verl/utils/test_module.py -------------------------------------------------------------------------------- /verl/verl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/README.md -------------------------------------------------------------------------------- /verl/verl/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/llama/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/llama/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/llama/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/checkpoint_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/llama/megatron/checkpoint_utils/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/checkpoint_utils/llama_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/HEAD/verl/verl/models/llama/megatron/checkpoint_utils/llama_saver.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/llama/megatron/layers/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/parallel_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/llama/megatron/layers/parallel_attention.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/parallel_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/llama/megatron/layers/parallel_decoder.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/parallel_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/llama/megatron/layers/parallel_linear.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/parallel_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/llama/megatron/layers/parallel_mlp.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/layers/parallel_rmsnorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/llama/megatron/layers/parallel_rmsnorm.py -------------------------------------------------------------------------------- /verl/verl/models/llama/megatron/modeling_llama_megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/llama/megatron/modeling_llama_megatron.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/mcore/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/config_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/mcore/config_converter.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/mcore/loader.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/model_forward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/mcore/model_forward.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/model_initializer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/mcore/model_initializer.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/mcore/readme.md -------------------------------------------------------------------------------- /verl/verl/models/mcore/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/mcore/registry.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/saver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/mcore/saver.py -------------------------------------------------------------------------------- /verl/verl/models/mcore/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/mcore/util.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/qwen2/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/qwen2/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/checkpoint_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/qwen2/megatron/checkpoint_utils/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/checkpoint_utils/qwen2_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/HEAD/verl/verl/models/qwen2/megatron/checkpoint_utils/qwen2_saver.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/qwen2/megatron/layers/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/parallel_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/qwen2/megatron/layers/parallel_attention.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/parallel_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/qwen2/megatron/layers/parallel_decoder.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/parallel_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/qwen2/megatron/layers/parallel_linear.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/parallel_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/qwen2/megatron/layers/parallel_mlp.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/layers/parallel_rmsnorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/qwen2/megatron/layers/parallel_rmsnorm.py -------------------------------------------------------------------------------- /verl/verl/models/qwen2/megatron/modeling_qwen2_megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/qwen2/megatron/modeling_qwen2_megatron.py -------------------------------------------------------------------------------- /verl/verl/models/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/registry.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/transformers/__init__.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/transformers/llama.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/transformers/monkey_patch.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/qwen2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/transformers/qwen2.py -------------------------------------------------------------------------------- /verl/verl/models/transformers/qwen2_vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/transformers/qwen2_vl.py -------------------------------------------------------------------------------- /verl/verl/models/weight_loader_registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/models/weight_loader_registry.py -------------------------------------------------------------------------------- /verl/verl/protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/protocol.py -------------------------------------------------------------------------------- /verl/verl/single_controller/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/single_controller/__init__.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/single_controller/base/__init__.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/single_controller/base/decorator.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/single_controller/base/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/megatron/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/single_controller/base/megatron/worker.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/megatron/worker_group.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/single_controller/base/megatron/worker_group.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/register_center/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/single_controller/base/register_center/__init__.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/register_center/ray.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/single_controller/base/register_center/ray.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/single_controller/base/worker.py -------------------------------------------------------------------------------- /verl/verl/single_controller/base/worker_group.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/single_controller/base/worker_group.py -------------------------------------------------------------------------------- /verl/verl/single_controller/ray/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/single_controller/ray/__init__.py -------------------------------------------------------------------------------- /verl/verl/single_controller/ray/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/single_controller/ray/base.py -------------------------------------------------------------------------------- /verl/verl/single_controller/ray/megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/single_controller/ray/megatron.py -------------------------------------------------------------------------------- /verl/verl/third_party/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/sglang/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/sglang/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/sglang/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/sglang/parallel_state.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_3_1/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_3_1/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_3_1/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_3_1/arg_utils.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_3_1/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_3_1/config.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_3_1/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_3_1/llm.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_3_1/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_3_1/model_loader.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_3_1/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_3_1/model_runner.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_3_1/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_3_1/parallel_state.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_3_1/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_3_1/tokenizer.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_3_1/weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_3_1/weight_loaders.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_3_1/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_3_1/worker.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_4_2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_4_2/__init__.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_4_2/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_4_2/arg_utils.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_4_2/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_4_2/config.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_4_2/dtensor_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_4_2/dtensor_weight_loaders.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_4_2/hf_weight_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_4_2/hf_weight_loader.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_4_2/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_4_2/llm.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_4_2/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_4_2/llm_engine_sp.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_4_2/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_4_2/model_loader.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_4_2/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_4_2/model_runner.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_4_2/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_4_2/parallel_state.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_4_2/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_4_2/tokenizer.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_4_2/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_4_2/worker.py -------------------------------------------------------------------------------- /verl/verl/third_party/vllm/vllm_v_0_5_4/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/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/YujunZhou/EVOL-RL/HEAD/verl/verl/third_party/vllm/vllm_v_0_6_3/worker.py -------------------------------------------------------------------------------- /verl/verl/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/__init__.py -------------------------------------------------------------------------------- /verl/verl/trainer/config/evaluation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/config/evaluation.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/config/generation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/config/generation.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/config/ppo_megatron_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/config/ppo_megatron_trainer.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/config/ppo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/config/ppo_trainer.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/config/sft_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/config/sft_trainer.yaml -------------------------------------------------------------------------------- /verl/verl/trainer/fsdp_sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/fsdp_sft_trainer.py -------------------------------------------------------------------------------- /verl/verl/trainer/main_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/main_eval.py -------------------------------------------------------------------------------- /verl/verl/trainer/main_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/main_generation.py -------------------------------------------------------------------------------- /verl/verl/trainer/main_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/main_ppo.py -------------------------------------------------------------------------------- /verl/verl/trainer/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/ppo/__init__.py -------------------------------------------------------------------------------- /verl/verl/trainer/ppo/core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/ppo/core_algos.py -------------------------------------------------------------------------------- /verl/verl/trainer/ppo/metric_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/ppo/metric_utils.py -------------------------------------------------------------------------------- /verl/verl/trainer/ppo/ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/ppo/ray_trainer.py -------------------------------------------------------------------------------- /verl/verl/trainer/runtime_env.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/trainer/runtime_env.yaml -------------------------------------------------------------------------------- /verl/verl/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/checkpoint/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/checkpoint/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/checkpoint/checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/checkpoint/checkpoint_manager.py -------------------------------------------------------------------------------- /verl/verl/utils/checkpoint/fsdp_checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/checkpoint/fsdp_checkpoint_manager.py -------------------------------------------------------------------------------- /verl/verl/utils/checkpoint/megatron_checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/checkpoint/megatron_checkpoint_manager.py -------------------------------------------------------------------------------- /verl/verl/utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/config.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/dataset/README.md -------------------------------------------------------------------------------- /verl/verl/utils/dataset/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/dataset/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/multiturn_sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/dataset/multiturn_sft_dataset.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/rl_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/dataset/rl_dataset.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/rm_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/dataset/rm_dataset.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/dataset/sft_dataset.py -------------------------------------------------------------------------------- /verl/verl/utils/dataset/vision_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/dataset/vision_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/debug/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/debug/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/debug/performance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/debug/performance.py -------------------------------------------------------------------------------- /verl/verl/utils/debug/trajectory_tracker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/debug/trajectory_tracker.py -------------------------------------------------------------------------------- /verl/verl/utils/distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/distributed.py -------------------------------------------------------------------------------- /verl/verl/utils/flops_counter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/flops_counter.py -------------------------------------------------------------------------------- /verl/verl/utils/fs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/fs.py -------------------------------------------------------------------------------- /verl/verl/utils/fsdp_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/fsdp_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/hdfs_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/hdfs_io.py -------------------------------------------------------------------------------- /verl/verl/utils/import_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/import_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/logger/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/logger/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/logger/aggregate_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/logger/aggregate_logger.py -------------------------------------------------------------------------------- /verl/verl/utils/logging_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/logging_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/megatron/memory.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/megatron/optimizer.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/pipeline_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/megatron/pipeline_parallel.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/sequence_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/megatron/sequence_parallel.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron/tensor_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/megatron/tensor_parallel.py -------------------------------------------------------------------------------- /verl/verl/utils/megatron_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/megatron_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/memory_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/memory_buffer.py -------------------------------------------------------------------------------- /verl/verl/utils/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/model.py -------------------------------------------------------------------------------- /verl/verl/utils/py_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/py_functional.py -------------------------------------------------------------------------------- /verl/verl/utils/ray_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/ray_utils.py -------------------------------------------------------------------------------- /verl/verl/utils/rendezvous/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/rendezvous/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/rendezvous/ray_backend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/rendezvous/ray_backend.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/geo3k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/geo3k.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/gsm8k.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/math.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/math_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/math_batch.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/math_dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/math_dapo.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/math_verify.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/math_verify.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_code/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/prime_code/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_code/testing_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/prime_code/testing_util.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_code/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/prime_code/utils.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_math/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/prime_math/__init__.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_math/grader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/prime_math/grader.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/prime_math/math_normalize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/prime_math/math_normalize.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/ttrl/auto_extract.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/ttrl/auto_extract.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/ttrl/auto_verify.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/ttrl/auto_verify.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/ttrl/latex_clean.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/ttrl/latex_clean.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/ttrl/qwen/grader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/ttrl/qwen/grader.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/ttrl/qwen/math_grade.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/ttrl/qwen/math_grade.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/ttrl/qwen/math_normalize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/ttrl/qwen/math_normalize.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/ttrl/qwen/qwen_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/ttrl/qwen/qwen_eval.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/ttrl/qwen/qwen_math_parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/ttrl/qwen/qwen_math_parser.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/ttrl/qwen/simplerl_math_equal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/ttrl/qwen/simplerl_math_equal.py -------------------------------------------------------------------------------- /verl/verl/utils/reward_score/ttrl/ttt_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/reward_score/ttrl/ttt_metrics.py -------------------------------------------------------------------------------- /verl/verl/utils/seqlen_balancing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/seqlen_balancing.py -------------------------------------------------------------------------------- /verl/verl/utils/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/tokenizer.py -------------------------------------------------------------------------------- /verl/verl/utils/torch_dtypes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/torch_dtypes.py -------------------------------------------------------------------------------- /verl/verl/utils/torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/torch_functional.py -------------------------------------------------------------------------------- /verl/verl/utils/tracking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/tracking.py -------------------------------------------------------------------------------- /verl/verl/utils/ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/utils/ulysses.py -------------------------------------------------------------------------------- /verl/verl/version/version: -------------------------------------------------------------------------------- 1 | 0.2.0.dev 2 | -------------------------------------------------------------------------------- /verl/verl/workers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/actor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/actor/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/actor/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/actor/base.py -------------------------------------------------------------------------------- /verl/verl/workers/actor/dp_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/actor/dp_actor.py -------------------------------------------------------------------------------- /verl/verl/workers/actor/megatron_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/actor/megatron_actor.py -------------------------------------------------------------------------------- /verl/verl/workers/critic/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/critic/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/critic/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/critic/base.py -------------------------------------------------------------------------------- /verl/verl/workers/critic/dp_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/critic/dp_critic.py -------------------------------------------------------------------------------- /verl/verl/workers/critic/megatron_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/critic/megatron_critic.py -------------------------------------------------------------------------------- /verl/verl/workers/fsdp_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/fsdp_workers.py -------------------------------------------------------------------------------- /verl/verl/workers/megatron_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/megatron_workers.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/reward_manager/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/reward_manager/batch.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/reward_manager/dapo.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/reward_manager/naive.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/prime.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/reward_manager/prime.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/semantic_novelty.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/reward_manager/semantic_novelty.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_manager/ttrl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/reward_manager/ttrl.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/reward_model/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_model/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/reward_model/base.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_model/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/reward_model/megatron/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/reward_model/megatron/reward_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/reward_model/megatron/reward_model.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/rollout/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/rollout/base.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/hf_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/rollout/hf_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/naive/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/rollout/naive/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/naive/naive_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/rollout/naive/naive_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/sglang_rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/rollout/sglang_rollout/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/sglang_rollout/sglang_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/rollout/sglang_rollout/sglang_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/rollout/tokenizer.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/rollout/vllm_rollout/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/fire_vllm_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/rollout/vllm_rollout/fire_vllm_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/vllm_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/rollout/vllm_rollout/vllm_rollout.py -------------------------------------------------------------------------------- /verl/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/sharding_manager/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/sharding_manager/base.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/fsdp_sglang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/sharding_manager/fsdp_sglang.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/fsdp_ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/sharding_manager/fsdp_ulysses.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/fsdp_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/sharding_manager/fsdp_vllm.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/megatron_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/sharding_manager/megatron_vllm.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/patch/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/sharding_manager/patch/__init__.py -------------------------------------------------------------------------------- /verl/verl/workers/sharding_manager/patch/fsdp_vllm_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/verl/workers/sharding_manager/patch/fsdp_vllm_patch.py -------------------------------------------------------------------------------- /verl/vllm_embedding_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/YujunZhou/EVOL-RL/HEAD/verl/vllm_embedding_api.py --------------------------------------------------------------------------------