├── .gemini └── config.yaml ├── .github └── workflows │ ├── cpu_ci.yaml │ ├── gpu_ci.yaml │ └── gpu_e2e_ci.yaml ├── .gitignore ├── .gitmodules ├── .pre-commit-config.yaml ├── .readthedocs.yaml ├── LICENSE ├── README.md ├── docker ├── Dockerfile ├── Dockerfile.megatron └── Dockerfile.ray244 ├── format.sh ├── pyproject.toml ├── skyagent ├── .env.example ├── .gitignore ├── .gitmodules ├── README.md ├── examples │ ├── run_openai │ │ ├── README.md │ │ ├── openai_react.yaml │ │ └── run_openai_react.py │ ├── run_skyrl │ │ ├── README.md │ │ ├── run_skyrl_oh.py │ │ ├── skyrl_oh.sh │ │ ├── skyrl_oh.yaml │ │ ├── skyrl_train_main.py │ │ └── trainer.py │ ├── run_verl │ │ ├── README.md │ │ ├── verl_main_ppo.py │ │ ├── verl_oh.sh │ │ ├── verl_oh.yaml │ │ └── verl_trainer.py │ └── skyrl_v0 │ │ └── README.md ├── pyproject.toml ├── skyagent │ ├── __init__.py │ ├── agents │ │ ├── __init__.py │ │ ├── base.py │ │ ├── mapping.py │ │ ├── oh_codeact │ │ │ ├── __init__.py │ │ │ ├── codeact_agent.py │ │ │ └── codeact_runner.py │ │ └── react │ │ │ ├── __init__.py │ │ │ ├── react_agent.py │ │ │ └── react_runner.py │ ├── auto.py │ ├── config │ │ ├── __init__.py │ │ └── configuration_utils.py │ ├── dispatcher │ │ ├── __init__.py │ │ ├── async_utils.py │ │ └── dispatchers.py │ ├── functional │ │ ├── __init__.py │ │ ├── chat_template.py │ │ ├── function_calling.py │ │ ├── functions.py │ │ └── templates │ │ │ └── qwen3_acc_thinking.jinja2 │ ├── integrations │ │ ├── __init__.py │ │ ├── base.py │ │ ├── openai.py │ │ ├── skyrl_train │ │ │ ├── __init__.py │ │ │ └── skyrl_train_backend.py │ │ └── verl │ │ │ ├── __init__.py │ │ │ ├── skagent_async_vllm_server.py │ │ │ ├── skyagent_async_sglang_server.py │ │ │ ├── upload_utils.py │ │ │ ├── verl_async_manager.py │ │ │ └── verl_backend.py │ ├── tasks │ │ ├── __init__.py │ │ ├── base.py │ │ ├── general_react │ │ │ ├── __init__.py │ │ │ └── utils.py │ │ ├── swebench │ │ │ ├── __init__.py │ │ │ ├── r2e_utils.py │ │ │ ├── scripts │ │ │ │ └── setup │ │ │ │ │ ├── instance_r2e_entry.sh │ │ │ │ │ ├── instance_swe_entry.sh │ │ │ │ │ └── swe_entry.sh │ │ │ └── utils.py │ │ └── verifiers │ │ │ ├── __init__.py │ │ │ ├── coder1 │ │ │ ├── __init__.py │ │ │ ├── sandboxfusion_exec.py │ │ │ ├── unsafe_local_exec.py │ │ │ └── utils.py │ │ │ ├── naive_dapo.py │ │ │ ├── prime_math │ │ │ ├── __init__.py │ │ │ ├── grader.py │ │ │ └── math_normalize.py │ │ │ ├── py_functional.py │ │ │ ├── sandbox_fusion │ │ │ └── utils.py │ │ │ └── torl │ │ │ ├── __init__.py │ │ │ ├── eval.py │ │ │ └── math_verify.py │ └── tools │ │ ├── __init__.py │ │ ├── base.py │ │ ├── finish.py │ │ ├── prompt.py │ │ ├── sandbox_fusion.py │ │ ├── search_engine.py │ │ └── web_browser.py ├── skyrl-train ├── tests │ ├── react_task_tests │ │ ├── no_tool.yaml │ │ ├── react_finish_only.yaml │ │ ├── react_interpreter.yaml │ │ ├── test.py │ │ ├── test_sandbox_endpoint.py │ │ └── test_stem.py │ ├── test_openai_backend.py │ ├── test_openai_oh.py │ └── test_openai_oh.yaml ├── uv.lock └── vis_trace.py ├── skyrl-gym ├── README.md ├── pyproject.toml ├── skyrl_gym │ ├── __init__.py │ ├── core.py │ ├── envs │ │ ├── README.md │ │ ├── __init__.py │ │ ├── aime │ │ │ ├── env.py │ │ │ └── utils.py │ │ ├── base_text_env.py │ │ ├── gsm8k │ │ │ ├── env.py │ │ │ ├── multi_turn_env.py │ │ │ └── utils.py │ │ ├── lcb │ │ │ ├── env.py │ │ │ └── livecodebench.py │ │ ├── registration.py │ │ ├── search │ │ │ ├── env.py │ │ │ └── utils.py │ │ ├── searchcode │ │ │ └── env.py │ │ └── sql │ │ │ ├── env.py │ │ │ └── utils.py │ ├── error.py │ └── tools │ │ ├── __init__.py │ │ ├── core.py │ │ ├── python.py │ │ ├── search.py │ │ └── sql.py ├── tests │ ├── test_aime.py │ ├── test_gsm8k.py │ ├── test_lcb.py │ ├── test_search.py │ ├── test_searchcode.py │ └── test_sql.py └── uv.lock └── skyrl-train ├── .env.example ├── .env.llm_judge ├── .gitignore ├── README.md ├── ci ├── anyscale_gpu_ci.yaml ├── anyscale_gpu_e2e_test.yaml ├── gpu_ci_run.sh └── gpu_e2e_test_run.sh ├── docs ├── algorithms │ ├── custom_algorithms.rst │ └── dapo.rst ├── api │ ├── constants.rst │ ├── data.rst │ ├── entrypoint.rst │ ├── env.rst │ ├── generator.rst │ ├── registry.rst │ ├── tools.rst │ └── trainer.rst ├── build.sh ├── checkpointing-logging │ └── checkpointing.rst ├── conf.py ├── configuration │ ├── config.rst │ └── placement.rst ├── datasets │ └── dataset-preparation.rst ├── examples │ ├── flash_rl.rst │ ├── llm_as_a_judge.rst │ ├── mini_swe_agent.rst │ ├── multi_turn_text2sql.rst │ ├── ppo.rst │ ├── remote_server.rst │ ├── search.rst │ └── training_backends.rst ├── getting-started │ ├── development.rst │ ├── images │ │ └── system-overview.png │ ├── installation.rst │ ├── overview.rst │ └── quickstart.rst ├── index.rst ├── recipes │ ├── searchr1.rst │ └── skyrl-sql.rst ├── skyagent │ ├── agent-overview.rst │ └── images │ │ ├── dispatcher_skyagent.png │ │ └── generate_trajectory.png ├── troubleshooting │ └── troubleshooting.rst └── tutorials │ ├── async.rst │ ├── new_env.rst │ ├── skyrl_gym_generator.rst │ └── tools_guide.rst ├── examples ├── algorithms │ ├── clip_cov_kl_cov │ │ ├── README.md │ │ ├── run_clip_cov.sh │ │ └── run_kl_cov.sh │ ├── custom_advantage_estimator │ │ ├── main_custom_adv_est.py │ │ └── run_custom_adv_est.sh │ ├── custom_policy_loss │ │ ├── main_custom_policy_loss.py │ │ └── run_custom_policy_loss.sh │ ├── dapo │ │ ├── data_preprocess_dapo_aime.py │ │ ├── main_dapo.py │ │ ├── prepare_dapo_data.sh │ │ ├── run_dapo_aime.sh │ │ └── run_dapo_gsm8k.sh │ ├── drgrpo │ │ └── run_drgrpo_gsm8k.sh │ ├── reinforce++ │ │ └── run_reinforce++.sh │ └── rloo │ │ └── run_rloo.sh ├── async │ ├── README.md │ ├── __init__.py │ ├── async_run_gsm8k.sh │ ├── async_trainer.py │ └── main_async.py ├── flash_rl │ ├── .env.0.5b_int8 │ ├── .env.fp8 │ ├── .env.int8 │ ├── flash_rl_engine.py │ ├── main_dapo_flashrl.py │ ├── run_dapo_gsm8k_flashrl_0.5b_fp8.sh │ ├── run_dapo_gsm8k_flashrl_0.5b_int8.sh │ ├── run_dapo_gsm8k_flashrl_32b_int8.sh │ ├── run_dapo_repro_flashrl_0.5b_int8.sh │ └── run_dapo_repro_flashrl_32b_int8.sh ├── gsm8k │ ├── gsm8k_dataset.py │ ├── run_32b_gsm8k.sh │ ├── run_generation_gsm8k.sh │ └── run_gsm8k.sh ├── livecodebench │ ├── lcb.md │ ├── lcb_dataset.py │ ├── lcb_download.py │ └── run_lcb.sh ├── llm_as_a_judge │ ├── gsm8k_dataset_judge.py │ ├── llm_judge_env.py │ ├── main_llm_judge.py │ └── run_llm_judge.sh ├── mini_swe_agent │ ├── .env.miniswe │ ├── README.md │ ├── litellm.json │ ├── main_mini_swe.py │ ├── mini_swe_generator.py │ ├── mini_swe_utils.py │ ├── preprocess_swegym.py │ ├── run_mini_swe_30B.sh │ ├── run_mini_swe_8B.sh │ └── swebench.yaml ├── moe │ ├── README.md │ └── run_qwen1_5_MoE_A2_7B.sh ├── multiply │ ├── env.py │ ├── main_multiply.py │ ├── multiply_dataset.py │ └── run_multiply.sh ├── ppo │ └── run_ppo.sh ├── remote_inference_engine │ ├── run_remote.sh │ ├── run_sglang_server.sh │ └── run_vllm_server.sh ├── search │ ├── README.md │ ├── retriever │ │ ├── retrieval_launch.sh │ │ └── retrieval_server.py │ ├── run_search.sh │ ├── run_search_conversation_format.sh │ ├── searchr1_dataset.py │ └── searchr1_download.py ├── terminal_bench │ ├── README.md │ ├── entrypoints │ │ ├── main_tbench.py │ │ └── main_tbench_generate.py │ ├── generator │ │ └── terminal_bench_generator.py │ ├── run_tbench.sh │ ├── run_tbench_gen.sh │ └── terminal_bench_config │ │ └── terminal_bench.yaml ├── text_to_sql │ ├── run_skyrl_sql.sh │ ├── run_skyrl_sql_conversation_format.sh │ ├── run_sql_deepspeed.sh │ ├── run_sql_fsdp.sh │ ├── run_sql_fsdp_2node.sh │ └── sql.md ├── tis_correction │ ├── main_tis_dapo.py │ └── run_dapo_tis.sh ├── training_backends │ ├── deepspeed │ │ └── run_deepspeed.sh │ ├── fsdp │ │ ├── run_fsdp.sh │ │ └── run_fsdp2.sh │ ├── megatron │ │ ├── run_fsdp_baseline.sh │ │ ├── run_megatron.sh │ │ ├── run_megatron_moonlight.sh │ │ ├── run_megatron_qwen3-235b-a22b.sh │ │ ├── run_megatron_qwen3-30b-a3b.sh │ │ └── run_search_megatron.sh │ └── run_no_seq_pack.sh └── turn_level_rewards │ ├── README.md │ ├── gsm8k_multi_turn_dataset.py │ └── run_gsm8k_multi_turn.sh ├── integrations └── verifiers │ ├── README.md │ ├── entrypoints │ └── main_verifiers.py │ ├── install_environment.py │ ├── prepare_dataset.py │ ├── run_verifiers.sh │ └── verifiers_generator.py ├── pyproject.toml ├── scripts ├── full_context │ ├── README.md │ ├── __init__.py │ ├── main_full_ctx.py │ ├── run_full_ctx.sh │ └── trainer_full_ctx.py ├── launch_multiple_remote_servers.py └── multi_node_nccl_test.py ├── skyrl-gym ├── skyrl_train ├── __init__.py ├── config │ ├── deepspeed_config │ │ ├── eval.yaml │ │ └── train.yaml │ ├── megatron_config │ │ ├── policy.yaml │ │ └── ref.yaml │ ├── ppo_base_config.yaml │ └── skyrl_gym_config │ │ └── default.yaml ├── dataset │ ├── __init__.py │ ├── dataset.py │ ├── preprocess.py │ └── replay_buffer.py ├── distributed │ ├── __init__.py │ ├── deepspeed_strategy.py │ ├── dispatch.py │ ├── fsdp_strategy.py │ ├── fsdp_utils.py │ ├── megatron │ │ ├── megatron_strategy.py │ │ ├── megatron_utils.py │ │ ├── model_utils.py │ │ └── optimizer.py │ ├── strategy.py │ ├── ulysses │ │ ├── __init__.py │ │ ├── monkey_patch.py │ │ └── utils.py │ └── utils.py ├── entrypoints │ ├── main_base.py │ └── main_generate.py ├── evaluate.py ├── generators │ ├── __init__.py │ ├── base.py │ ├── skyrl_gym_generator.py │ └── utils.py ├── inference_engines │ ├── __init__.py │ ├── base.py │ ├── inference_engine_client.py │ ├── inference_engine_client_http_endpoint.py │ ├── ray_wrapped_inference_engine.py │ ├── remote_inference_engine.py │ ├── sglang │ │ ├── sglang_engine.py │ │ └── sglang_server.py │ ├── utils.py │ └── vllm │ │ ├── vllm_engine.py │ │ └── vllm_server.py ├── models.py ├── trainer.py ├── training_batch.py ├── utils │ ├── __init__.py │ ├── constants.py │ ├── io.py │ ├── ppo_utils.py │ ├── profiler.py │ ├── torch_utils.py │ ├── tracking.py │ ├── trainer_utils.py │ └── utils.py ├── weights_manager.py └── workers │ ├── __init__.py │ ├── deepspeed │ └── deepspeed_worker.py │ ├── fsdp │ └── fsdp_worker.py │ ├── megatron │ ├── megatron_policy.py │ └── megatron_worker.py │ ├── worker.py │ └── worker_utils.py ├── tests ├── __init__.py ├── cpu │ ├── __init__.py │ ├── algorithms │ │ └── test_losses.py │ ├── conftest.py │ ├── dataset │ │ ├── test_dataset.py │ │ └── test_preprocess.py │ ├── distributed │ │ ├── test_dispatch.py │ │ └── test_ulysses.py │ ├── generators │ │ ├── test_skyrl_gym_generator.py │ │ ├── test_skyrl_gym_generator_chat_templating.py │ │ └── test_utils.py │ ├── inf_engines │ │ ├── test_inference_engine_client.py │ │ └── test_route_prompts_to_engines.py │ ├── models │ │ └── test_models.py │ ├── test_eval.py │ ├── test_generator_postprocess.py │ ├── test_train_batch.py │ ├── test_trainer.py │ ├── test_trainer_utils.py │ ├── util.py │ └── utils │ │ ├── test_io.py │ │ ├── test_ppo_utils.py │ │ └── test_torch_utils.py └── gpu │ ├── __init__.py │ ├── conftest.py │ ├── gpu_ci │ ├── __init__.py │ ├── conftest.py │ ├── test_engine_generation.py │ ├── test_inference_engine_client_http_endpoint.py │ ├── test_models.py │ ├── test_save_load_checkpoint.py │ ├── test_skyrl_gym_generator.py │ ├── test_train_batch.py │ ├── test_trainer_full_checkpointing.py │ └── test_verifiers_generator.py │ ├── gpu_e2e_test │ └── gsm8k_colocate.sh │ ├── runner.py │ ├── test_expert_parallel_inference.py │ ├── test_grpo_sp_sanity.py │ ├── test_main_generate.py │ ├── test_megatron_worker.py │ ├── test_multi_node_pg.py │ ├── test_policy_local_engines_e2e.py │ ├── test_ppo_train.py │ ├── test_save_load_model.py │ ├── test_skyrl_gym_generator.py │ ├── test_training_step.py │ ├── test_worker_offload.py │ └── utils.py └── uv.lock /.gemini/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/.gemini/config.yaml -------------------------------------------------------------------------------- /.github/workflows/cpu_ci.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/.github/workflows/cpu_ci.yaml -------------------------------------------------------------------------------- /.github/workflows/gpu_ci.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/.github/workflows/gpu_ci.yaml -------------------------------------------------------------------------------- /.github/workflows/gpu_e2e_ci.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/.github/workflows/gpu_e2e_ci.yaml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/.gitignore -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/.gitmodules -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /.readthedocs.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/.readthedocs.yaml -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/README.md -------------------------------------------------------------------------------- /docker/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/docker/Dockerfile -------------------------------------------------------------------------------- /docker/Dockerfile.megatron: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/docker/Dockerfile.megatron -------------------------------------------------------------------------------- /docker/Dockerfile.ray244: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/docker/Dockerfile.ray244 -------------------------------------------------------------------------------- /format.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/format.sh -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/pyproject.toml -------------------------------------------------------------------------------- /skyagent/.env.example: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/.env.example -------------------------------------------------------------------------------- /skyagent/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/.gitignore -------------------------------------------------------------------------------- /skyagent/.gitmodules: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/.gitmodules -------------------------------------------------------------------------------- /skyagent/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/README.md -------------------------------------------------------------------------------- /skyagent/examples/run_openai/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/run_openai/README.md -------------------------------------------------------------------------------- /skyagent/examples/run_openai/openai_react.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/run_openai/openai_react.yaml -------------------------------------------------------------------------------- /skyagent/examples/run_openai/run_openai_react.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/run_openai/run_openai_react.py -------------------------------------------------------------------------------- /skyagent/examples/run_skyrl/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/run_skyrl/README.md -------------------------------------------------------------------------------- /skyagent/examples/run_skyrl/run_skyrl_oh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/run_skyrl/run_skyrl_oh.py -------------------------------------------------------------------------------- /skyagent/examples/run_skyrl/skyrl_oh.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/run_skyrl/skyrl_oh.sh -------------------------------------------------------------------------------- /skyagent/examples/run_skyrl/skyrl_oh.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/run_skyrl/skyrl_oh.yaml -------------------------------------------------------------------------------- /skyagent/examples/run_skyrl/skyrl_train_main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/run_skyrl/skyrl_train_main.py -------------------------------------------------------------------------------- /skyagent/examples/run_skyrl/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/run_skyrl/trainer.py -------------------------------------------------------------------------------- /skyagent/examples/run_verl/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/run_verl/README.md -------------------------------------------------------------------------------- /skyagent/examples/run_verl/verl_main_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/run_verl/verl_main_ppo.py -------------------------------------------------------------------------------- /skyagent/examples/run_verl/verl_oh.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/run_verl/verl_oh.sh -------------------------------------------------------------------------------- /skyagent/examples/run_verl/verl_oh.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/run_verl/verl_oh.yaml -------------------------------------------------------------------------------- /skyagent/examples/run_verl/verl_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/run_verl/verl_trainer.py -------------------------------------------------------------------------------- /skyagent/examples/skyrl_v0/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/examples/skyrl_v0/README.md -------------------------------------------------------------------------------- /skyagent/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/pyproject.toml -------------------------------------------------------------------------------- /skyagent/skyagent/__init__.py: -------------------------------------------------------------------------------- 1 | from .auto import AutoAgentRunner 2 | -------------------------------------------------------------------------------- /skyagent/skyagent/agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/agents/__init__.py -------------------------------------------------------------------------------- /skyagent/skyagent/agents/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/agents/base.py -------------------------------------------------------------------------------- /skyagent/skyagent/agents/mapping.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/agents/mapping.py -------------------------------------------------------------------------------- /skyagent/skyagent/agents/oh_codeact/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/agents/oh_codeact/__init__.py -------------------------------------------------------------------------------- /skyagent/skyagent/agents/oh_codeact/codeact_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/agents/oh_codeact/codeact_agent.py -------------------------------------------------------------------------------- /skyagent/skyagent/agents/oh_codeact/codeact_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/agents/oh_codeact/codeact_runner.py -------------------------------------------------------------------------------- /skyagent/skyagent/agents/react/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/agents/react/__init__.py -------------------------------------------------------------------------------- /skyagent/skyagent/agents/react/react_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/agents/react/react_agent.py -------------------------------------------------------------------------------- /skyagent/skyagent/agents/react/react_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/agents/react/react_runner.py -------------------------------------------------------------------------------- /skyagent/skyagent/auto.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/auto.py -------------------------------------------------------------------------------- /skyagent/skyagent/config/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyagent/skyagent/config/configuration_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/config/configuration_utils.py -------------------------------------------------------------------------------- /skyagent/skyagent/dispatcher/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyagent/skyagent/dispatcher/async_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/dispatcher/async_utils.py -------------------------------------------------------------------------------- /skyagent/skyagent/dispatcher/dispatchers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/dispatcher/dispatchers.py -------------------------------------------------------------------------------- /skyagent/skyagent/functional/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyagent/skyagent/functional/chat_template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/functional/chat_template.py -------------------------------------------------------------------------------- /skyagent/skyagent/functional/function_calling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/functional/function_calling.py -------------------------------------------------------------------------------- /skyagent/skyagent/functional/functions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/functional/functions.py -------------------------------------------------------------------------------- /skyagent/skyagent/functional/templates/qwen3_acc_thinking.jinja2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/functional/templates/qwen3_acc_thinking.jinja2 -------------------------------------------------------------------------------- /skyagent/skyagent/integrations/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/integrations/__init__.py -------------------------------------------------------------------------------- /skyagent/skyagent/integrations/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/integrations/base.py -------------------------------------------------------------------------------- /skyagent/skyagent/integrations/openai.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/integrations/openai.py -------------------------------------------------------------------------------- /skyagent/skyagent/integrations/skyrl_train/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/integrations/skyrl_train/__init__.py -------------------------------------------------------------------------------- /skyagent/skyagent/integrations/skyrl_train/skyrl_train_backend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/integrations/skyrl_train/skyrl_train_backend.py -------------------------------------------------------------------------------- /skyagent/skyagent/integrations/verl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/integrations/verl/__init__.py -------------------------------------------------------------------------------- /skyagent/skyagent/integrations/verl/skagent_async_vllm_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/integrations/verl/skagent_async_vllm_server.py -------------------------------------------------------------------------------- /skyagent/skyagent/integrations/verl/skyagent_async_sglang_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/integrations/verl/skyagent_async_sglang_server.py -------------------------------------------------------------------------------- /skyagent/skyagent/integrations/verl/upload_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/integrations/verl/upload_utils.py -------------------------------------------------------------------------------- /skyagent/skyagent/integrations/verl/verl_async_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/integrations/verl/verl_async_manager.py -------------------------------------------------------------------------------- /skyagent/skyagent/integrations/verl/verl_backend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/integrations/verl/verl_backend.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/base.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/general_react/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/general_react/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/general_react/utils.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/swebench/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/swebench/r2e_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/swebench/r2e_utils.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/swebench/scripts/setup/instance_r2e_entry.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/swebench/scripts/setup/instance_r2e_entry.sh -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/swebench/scripts/setup/instance_swe_entry.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/swebench/scripts/setup/instance_swe_entry.sh -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/swebench/scripts/setup/swe_entry.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/swebench/scripts/setup/swe_entry.sh -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/swebench/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/swebench/utils.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/verifiers/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/verifiers/coder1/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/verifiers/coder1/__init__.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/verifiers/coder1/sandboxfusion_exec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/verifiers/coder1/sandboxfusion_exec.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/verifiers/coder1/unsafe_local_exec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/verifiers/coder1/unsafe_local_exec.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/verifiers/coder1/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/verifiers/coder1/utils.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/verifiers/naive_dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/verifiers/naive_dapo.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/verifiers/prime_math/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/verifiers/prime_math/__init__.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/verifiers/prime_math/grader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/verifiers/prime_math/grader.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/verifiers/prime_math/math_normalize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/verifiers/prime_math/math_normalize.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/verifiers/py_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/verifiers/py_functional.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/verifiers/sandbox_fusion/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/verifiers/sandbox_fusion/utils.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/verifiers/torl/__init__.py: -------------------------------------------------------------------------------- 1 | from .math_verify import compute_score -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/verifiers/torl/eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/verifiers/torl/eval.py -------------------------------------------------------------------------------- /skyagent/skyagent/tasks/verifiers/torl/math_verify.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tasks/verifiers/torl/math_verify.py -------------------------------------------------------------------------------- /skyagent/skyagent/tools/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tools/__init__.py -------------------------------------------------------------------------------- /skyagent/skyagent/tools/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tools/base.py -------------------------------------------------------------------------------- /skyagent/skyagent/tools/finish.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tools/finish.py -------------------------------------------------------------------------------- /skyagent/skyagent/tools/prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tools/prompt.py -------------------------------------------------------------------------------- /skyagent/skyagent/tools/sandbox_fusion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tools/sandbox_fusion.py -------------------------------------------------------------------------------- /skyagent/skyagent/tools/search_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tools/search_engine.py -------------------------------------------------------------------------------- /skyagent/skyagent/tools/web_browser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/skyagent/tools/web_browser.py -------------------------------------------------------------------------------- /skyagent/skyrl-train: -------------------------------------------------------------------------------- 1 | ../skyrl-train/ -------------------------------------------------------------------------------- /skyagent/tests/react_task_tests/no_tool.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/tests/react_task_tests/no_tool.yaml -------------------------------------------------------------------------------- /skyagent/tests/react_task_tests/react_finish_only.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/tests/react_task_tests/react_finish_only.yaml -------------------------------------------------------------------------------- /skyagent/tests/react_task_tests/react_interpreter.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/tests/react_task_tests/react_interpreter.yaml -------------------------------------------------------------------------------- /skyagent/tests/react_task_tests/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/tests/react_task_tests/test.py -------------------------------------------------------------------------------- /skyagent/tests/react_task_tests/test_sandbox_endpoint.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/tests/react_task_tests/test_sandbox_endpoint.py -------------------------------------------------------------------------------- /skyagent/tests/react_task_tests/test_stem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/tests/react_task_tests/test_stem.py -------------------------------------------------------------------------------- /skyagent/tests/test_openai_backend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/tests/test_openai_backend.py -------------------------------------------------------------------------------- /skyagent/tests/test_openai_oh.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/tests/test_openai_oh.py -------------------------------------------------------------------------------- /skyagent/tests/test_openai_oh.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/tests/test_openai_oh.yaml -------------------------------------------------------------------------------- /skyagent/uv.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/uv.lock -------------------------------------------------------------------------------- /skyagent/vis_trace.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyagent/vis_trace.py -------------------------------------------------------------------------------- /skyrl-gym/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/README.md -------------------------------------------------------------------------------- /skyrl-gym/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/pyproject.toml -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/__init__.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/core.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/README.md -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/__init__.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/aime/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/aime/env.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/aime/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/aime/utils.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/base_text_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/base_text_env.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/gsm8k/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/gsm8k/env.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/gsm8k/multi_turn_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/gsm8k/multi_turn_env.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/gsm8k/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/gsm8k/utils.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/lcb/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/lcb/env.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/lcb/livecodebench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/lcb/livecodebench.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/registration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/registration.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/search/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/search/env.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/search/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/search/utils.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/searchcode/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/searchcode/env.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/sql/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/sql/env.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/envs/sql/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/envs/sql/utils.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/error.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/error.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/tools/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/tools/__init__.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/tools/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/tools/core.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/tools/python.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/tools/python.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/tools/search.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/tools/search.py -------------------------------------------------------------------------------- /skyrl-gym/skyrl_gym/tools/sql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/skyrl_gym/tools/sql.py -------------------------------------------------------------------------------- /skyrl-gym/tests/test_aime.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/tests/test_aime.py -------------------------------------------------------------------------------- /skyrl-gym/tests/test_gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/tests/test_gsm8k.py -------------------------------------------------------------------------------- /skyrl-gym/tests/test_lcb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/tests/test_lcb.py -------------------------------------------------------------------------------- /skyrl-gym/tests/test_search.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/tests/test_search.py -------------------------------------------------------------------------------- /skyrl-gym/tests/test_searchcode.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/tests/test_searchcode.py -------------------------------------------------------------------------------- /skyrl-gym/tests/test_sql.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/tests/test_sql.py -------------------------------------------------------------------------------- /skyrl-gym/uv.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-gym/uv.lock -------------------------------------------------------------------------------- /skyrl-train/.env.example: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/.env.example -------------------------------------------------------------------------------- /skyrl-train/.env.llm_judge: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/.env.llm_judge -------------------------------------------------------------------------------- /skyrl-train/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/.gitignore -------------------------------------------------------------------------------- /skyrl-train/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/README.md -------------------------------------------------------------------------------- /skyrl-train/ci/anyscale_gpu_ci.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/ci/anyscale_gpu_ci.yaml -------------------------------------------------------------------------------- /skyrl-train/ci/anyscale_gpu_e2e_test.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/ci/anyscale_gpu_e2e_test.yaml -------------------------------------------------------------------------------- /skyrl-train/ci/gpu_ci_run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/ci/gpu_ci_run.sh -------------------------------------------------------------------------------- /skyrl-train/ci/gpu_e2e_test_run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/ci/gpu_e2e_test_run.sh -------------------------------------------------------------------------------- /skyrl-train/docs/algorithms/custom_algorithms.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/algorithms/custom_algorithms.rst -------------------------------------------------------------------------------- /skyrl-train/docs/algorithms/dapo.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/algorithms/dapo.rst -------------------------------------------------------------------------------- /skyrl-train/docs/api/constants.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/api/constants.rst -------------------------------------------------------------------------------- /skyrl-train/docs/api/data.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/api/data.rst -------------------------------------------------------------------------------- /skyrl-train/docs/api/entrypoint.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/api/entrypoint.rst -------------------------------------------------------------------------------- /skyrl-train/docs/api/env.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/api/env.rst -------------------------------------------------------------------------------- /skyrl-train/docs/api/generator.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/api/generator.rst -------------------------------------------------------------------------------- /skyrl-train/docs/api/registry.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/api/registry.rst -------------------------------------------------------------------------------- /skyrl-train/docs/api/tools.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/api/tools.rst -------------------------------------------------------------------------------- /skyrl-train/docs/api/trainer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/api/trainer.rst -------------------------------------------------------------------------------- /skyrl-train/docs/build.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/build.sh -------------------------------------------------------------------------------- /skyrl-train/docs/checkpointing-logging/checkpointing.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/checkpointing-logging/checkpointing.rst -------------------------------------------------------------------------------- /skyrl-train/docs/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/conf.py -------------------------------------------------------------------------------- /skyrl-train/docs/configuration/config.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/configuration/config.rst -------------------------------------------------------------------------------- /skyrl-train/docs/configuration/placement.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/configuration/placement.rst -------------------------------------------------------------------------------- /skyrl-train/docs/datasets/dataset-preparation.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/datasets/dataset-preparation.rst -------------------------------------------------------------------------------- /skyrl-train/docs/examples/flash_rl.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/examples/flash_rl.rst -------------------------------------------------------------------------------- /skyrl-train/docs/examples/llm_as_a_judge.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/examples/llm_as_a_judge.rst -------------------------------------------------------------------------------- /skyrl-train/docs/examples/mini_swe_agent.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/examples/mini_swe_agent.rst -------------------------------------------------------------------------------- /skyrl-train/docs/examples/multi_turn_text2sql.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/examples/multi_turn_text2sql.rst -------------------------------------------------------------------------------- /skyrl-train/docs/examples/ppo.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/examples/ppo.rst -------------------------------------------------------------------------------- /skyrl-train/docs/examples/remote_server.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/examples/remote_server.rst -------------------------------------------------------------------------------- /skyrl-train/docs/examples/search.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/examples/search.rst -------------------------------------------------------------------------------- /skyrl-train/docs/examples/training_backends.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/examples/training_backends.rst -------------------------------------------------------------------------------- /skyrl-train/docs/getting-started/development.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/getting-started/development.rst -------------------------------------------------------------------------------- /skyrl-train/docs/getting-started/images/system-overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/getting-started/images/system-overview.png -------------------------------------------------------------------------------- /skyrl-train/docs/getting-started/installation.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/getting-started/installation.rst -------------------------------------------------------------------------------- /skyrl-train/docs/getting-started/overview.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/getting-started/overview.rst -------------------------------------------------------------------------------- /skyrl-train/docs/getting-started/quickstart.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/getting-started/quickstart.rst -------------------------------------------------------------------------------- /skyrl-train/docs/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/index.rst -------------------------------------------------------------------------------- /skyrl-train/docs/recipes/searchr1.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/recipes/searchr1.rst -------------------------------------------------------------------------------- /skyrl-train/docs/recipes/skyrl-sql.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/recipes/skyrl-sql.rst -------------------------------------------------------------------------------- /skyrl-train/docs/skyagent/agent-overview.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/skyagent/agent-overview.rst -------------------------------------------------------------------------------- /skyrl-train/docs/skyagent/images/dispatcher_skyagent.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/skyagent/images/dispatcher_skyagent.png -------------------------------------------------------------------------------- /skyrl-train/docs/skyagent/images/generate_trajectory.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/skyagent/images/generate_trajectory.png -------------------------------------------------------------------------------- /skyrl-train/docs/troubleshooting/troubleshooting.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/troubleshooting/troubleshooting.rst -------------------------------------------------------------------------------- /skyrl-train/docs/tutorials/async.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/tutorials/async.rst -------------------------------------------------------------------------------- /skyrl-train/docs/tutorials/new_env.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/tutorials/new_env.rst -------------------------------------------------------------------------------- /skyrl-train/docs/tutorials/skyrl_gym_generator.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/tutorials/skyrl_gym_generator.rst -------------------------------------------------------------------------------- /skyrl-train/docs/tutorials/tools_guide.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/docs/tutorials/tools_guide.rst -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/clip_cov_kl_cov/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/clip_cov_kl_cov/README.md -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/clip_cov_kl_cov/run_clip_cov.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/clip_cov_kl_cov/run_clip_cov.sh -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/clip_cov_kl_cov/run_kl_cov.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/clip_cov_kl_cov/run_kl_cov.sh -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/custom_advantage_estimator/main_custom_adv_est.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/custom_advantage_estimator/main_custom_adv_est.py -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/custom_advantage_estimator/run_custom_adv_est.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/custom_advantage_estimator/run_custom_adv_est.sh -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/custom_policy_loss/main_custom_policy_loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/custom_policy_loss/main_custom_policy_loss.py -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/custom_policy_loss/run_custom_policy_loss.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/custom_policy_loss/run_custom_policy_loss.sh -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/dapo/data_preprocess_dapo_aime.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/dapo/data_preprocess_dapo_aime.py -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/dapo/main_dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/dapo/main_dapo.py -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/dapo/prepare_dapo_data.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/dapo/prepare_dapo_data.sh -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/dapo/run_dapo_aime.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/dapo/run_dapo_aime.sh -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/dapo/run_dapo_gsm8k.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/dapo/run_dapo_gsm8k.sh -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/drgrpo/run_drgrpo_gsm8k.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/drgrpo/run_drgrpo_gsm8k.sh -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/reinforce++/run_reinforce++.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/reinforce++/run_reinforce++.sh -------------------------------------------------------------------------------- /skyrl-train/examples/algorithms/rloo/run_rloo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/algorithms/rloo/run_rloo.sh -------------------------------------------------------------------------------- /skyrl-train/examples/async/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/async/README.md -------------------------------------------------------------------------------- /skyrl-train/examples/async/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyrl-train/examples/async/async_run_gsm8k.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/async/async_run_gsm8k.sh -------------------------------------------------------------------------------- /skyrl-train/examples/async/async_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/async/async_trainer.py -------------------------------------------------------------------------------- /skyrl-train/examples/async/main_async.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/async/main_async.py -------------------------------------------------------------------------------- /skyrl-train/examples/flash_rl/.env.0.5b_int8: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/flash_rl/.env.0.5b_int8 -------------------------------------------------------------------------------- /skyrl-train/examples/flash_rl/.env.fp8: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/flash_rl/.env.fp8 -------------------------------------------------------------------------------- /skyrl-train/examples/flash_rl/.env.int8: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/flash_rl/.env.int8 -------------------------------------------------------------------------------- /skyrl-train/examples/flash_rl/flash_rl_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/flash_rl/flash_rl_engine.py -------------------------------------------------------------------------------- /skyrl-train/examples/flash_rl/main_dapo_flashrl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/flash_rl/main_dapo_flashrl.py -------------------------------------------------------------------------------- /skyrl-train/examples/flash_rl/run_dapo_gsm8k_flashrl_0.5b_fp8.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/flash_rl/run_dapo_gsm8k_flashrl_0.5b_fp8.sh -------------------------------------------------------------------------------- /skyrl-train/examples/flash_rl/run_dapo_gsm8k_flashrl_0.5b_int8.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/flash_rl/run_dapo_gsm8k_flashrl_0.5b_int8.sh -------------------------------------------------------------------------------- /skyrl-train/examples/flash_rl/run_dapo_gsm8k_flashrl_32b_int8.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/flash_rl/run_dapo_gsm8k_flashrl_32b_int8.sh -------------------------------------------------------------------------------- /skyrl-train/examples/flash_rl/run_dapo_repro_flashrl_0.5b_int8.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/flash_rl/run_dapo_repro_flashrl_0.5b_int8.sh -------------------------------------------------------------------------------- /skyrl-train/examples/flash_rl/run_dapo_repro_flashrl_32b_int8.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/flash_rl/run_dapo_repro_flashrl_32b_int8.sh -------------------------------------------------------------------------------- /skyrl-train/examples/gsm8k/gsm8k_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/gsm8k/gsm8k_dataset.py -------------------------------------------------------------------------------- /skyrl-train/examples/gsm8k/run_32b_gsm8k.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/gsm8k/run_32b_gsm8k.sh -------------------------------------------------------------------------------- /skyrl-train/examples/gsm8k/run_generation_gsm8k.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/gsm8k/run_generation_gsm8k.sh -------------------------------------------------------------------------------- /skyrl-train/examples/gsm8k/run_gsm8k.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/gsm8k/run_gsm8k.sh -------------------------------------------------------------------------------- /skyrl-train/examples/livecodebench/lcb.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/livecodebench/lcb.md -------------------------------------------------------------------------------- /skyrl-train/examples/livecodebench/lcb_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/livecodebench/lcb_dataset.py -------------------------------------------------------------------------------- /skyrl-train/examples/livecodebench/lcb_download.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/livecodebench/lcb_download.py -------------------------------------------------------------------------------- /skyrl-train/examples/livecodebench/run_lcb.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/livecodebench/run_lcb.sh -------------------------------------------------------------------------------- /skyrl-train/examples/llm_as_a_judge/gsm8k_dataset_judge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/llm_as_a_judge/gsm8k_dataset_judge.py -------------------------------------------------------------------------------- /skyrl-train/examples/llm_as_a_judge/llm_judge_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/llm_as_a_judge/llm_judge_env.py -------------------------------------------------------------------------------- /skyrl-train/examples/llm_as_a_judge/main_llm_judge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/llm_as_a_judge/main_llm_judge.py -------------------------------------------------------------------------------- /skyrl-train/examples/llm_as_a_judge/run_llm_judge.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/llm_as_a_judge/run_llm_judge.sh -------------------------------------------------------------------------------- /skyrl-train/examples/mini_swe_agent/.env.miniswe: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/mini_swe_agent/.env.miniswe -------------------------------------------------------------------------------- /skyrl-train/examples/mini_swe_agent/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/mini_swe_agent/README.md -------------------------------------------------------------------------------- /skyrl-train/examples/mini_swe_agent/litellm.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/mini_swe_agent/litellm.json -------------------------------------------------------------------------------- /skyrl-train/examples/mini_swe_agent/main_mini_swe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/mini_swe_agent/main_mini_swe.py -------------------------------------------------------------------------------- /skyrl-train/examples/mini_swe_agent/mini_swe_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/mini_swe_agent/mini_swe_generator.py -------------------------------------------------------------------------------- /skyrl-train/examples/mini_swe_agent/mini_swe_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/mini_swe_agent/mini_swe_utils.py -------------------------------------------------------------------------------- /skyrl-train/examples/mini_swe_agent/preprocess_swegym.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/mini_swe_agent/preprocess_swegym.py -------------------------------------------------------------------------------- /skyrl-train/examples/mini_swe_agent/run_mini_swe_30B.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/mini_swe_agent/run_mini_swe_30B.sh -------------------------------------------------------------------------------- /skyrl-train/examples/mini_swe_agent/run_mini_swe_8B.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/mini_swe_agent/run_mini_swe_8B.sh -------------------------------------------------------------------------------- /skyrl-train/examples/mini_swe_agent/swebench.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/mini_swe_agent/swebench.yaml -------------------------------------------------------------------------------- /skyrl-train/examples/moe/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/moe/README.md -------------------------------------------------------------------------------- /skyrl-train/examples/moe/run_qwen1_5_MoE_A2_7B.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/moe/run_qwen1_5_MoE_A2_7B.sh -------------------------------------------------------------------------------- /skyrl-train/examples/multiply/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/multiply/env.py -------------------------------------------------------------------------------- /skyrl-train/examples/multiply/main_multiply.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/multiply/main_multiply.py -------------------------------------------------------------------------------- /skyrl-train/examples/multiply/multiply_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/multiply/multiply_dataset.py -------------------------------------------------------------------------------- /skyrl-train/examples/multiply/run_multiply.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/multiply/run_multiply.sh -------------------------------------------------------------------------------- /skyrl-train/examples/ppo/run_ppo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/ppo/run_ppo.sh -------------------------------------------------------------------------------- /skyrl-train/examples/remote_inference_engine/run_remote.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/remote_inference_engine/run_remote.sh -------------------------------------------------------------------------------- /skyrl-train/examples/remote_inference_engine/run_sglang_server.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/remote_inference_engine/run_sglang_server.sh -------------------------------------------------------------------------------- /skyrl-train/examples/remote_inference_engine/run_vllm_server.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/remote_inference_engine/run_vllm_server.sh -------------------------------------------------------------------------------- /skyrl-train/examples/search/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/search/README.md -------------------------------------------------------------------------------- /skyrl-train/examples/search/retriever/retrieval_launch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/search/retriever/retrieval_launch.sh -------------------------------------------------------------------------------- /skyrl-train/examples/search/retriever/retrieval_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/search/retriever/retrieval_server.py -------------------------------------------------------------------------------- /skyrl-train/examples/search/run_search.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/search/run_search.sh -------------------------------------------------------------------------------- /skyrl-train/examples/search/run_search_conversation_format.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/search/run_search_conversation_format.sh -------------------------------------------------------------------------------- /skyrl-train/examples/search/searchr1_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/search/searchr1_dataset.py -------------------------------------------------------------------------------- /skyrl-train/examples/search/searchr1_download.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/search/searchr1_download.py -------------------------------------------------------------------------------- /skyrl-train/examples/terminal_bench/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/terminal_bench/README.md -------------------------------------------------------------------------------- /skyrl-train/examples/terminal_bench/entrypoints/main_tbench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/terminal_bench/entrypoints/main_tbench.py -------------------------------------------------------------------------------- /skyrl-train/examples/terminal_bench/entrypoints/main_tbench_generate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/terminal_bench/entrypoints/main_tbench_generate.py -------------------------------------------------------------------------------- /skyrl-train/examples/terminal_bench/generator/terminal_bench_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/terminal_bench/generator/terminal_bench_generator.py -------------------------------------------------------------------------------- /skyrl-train/examples/terminal_bench/run_tbench.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/terminal_bench/run_tbench.sh -------------------------------------------------------------------------------- /skyrl-train/examples/terminal_bench/run_tbench_gen.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/terminal_bench/run_tbench_gen.sh -------------------------------------------------------------------------------- /skyrl-train/examples/terminal_bench/terminal_bench_config/terminal_bench.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/terminal_bench/terminal_bench_config/terminal_bench.yaml -------------------------------------------------------------------------------- /skyrl-train/examples/text_to_sql/run_skyrl_sql.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/text_to_sql/run_skyrl_sql.sh -------------------------------------------------------------------------------- /skyrl-train/examples/text_to_sql/run_skyrl_sql_conversation_format.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/text_to_sql/run_skyrl_sql_conversation_format.sh -------------------------------------------------------------------------------- /skyrl-train/examples/text_to_sql/run_sql_deepspeed.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/text_to_sql/run_sql_deepspeed.sh -------------------------------------------------------------------------------- /skyrl-train/examples/text_to_sql/run_sql_fsdp.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/text_to_sql/run_sql_fsdp.sh -------------------------------------------------------------------------------- /skyrl-train/examples/text_to_sql/run_sql_fsdp_2node.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/text_to_sql/run_sql_fsdp_2node.sh -------------------------------------------------------------------------------- /skyrl-train/examples/text_to_sql/sql.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/text_to_sql/sql.md -------------------------------------------------------------------------------- /skyrl-train/examples/tis_correction/main_tis_dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/tis_correction/main_tis_dapo.py -------------------------------------------------------------------------------- /skyrl-train/examples/tis_correction/run_dapo_tis.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/tis_correction/run_dapo_tis.sh -------------------------------------------------------------------------------- /skyrl-train/examples/training_backends/deepspeed/run_deepspeed.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/training_backends/deepspeed/run_deepspeed.sh -------------------------------------------------------------------------------- /skyrl-train/examples/training_backends/fsdp/run_fsdp.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/training_backends/fsdp/run_fsdp.sh -------------------------------------------------------------------------------- /skyrl-train/examples/training_backends/fsdp/run_fsdp2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/training_backends/fsdp/run_fsdp2.sh -------------------------------------------------------------------------------- /skyrl-train/examples/training_backends/megatron/run_fsdp_baseline.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/training_backends/megatron/run_fsdp_baseline.sh -------------------------------------------------------------------------------- /skyrl-train/examples/training_backends/megatron/run_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/training_backends/megatron/run_megatron.sh -------------------------------------------------------------------------------- /skyrl-train/examples/training_backends/megatron/run_megatron_moonlight.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/training_backends/megatron/run_megatron_moonlight.sh -------------------------------------------------------------------------------- /skyrl-train/examples/training_backends/megatron/run_megatron_qwen3-235b-a22b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/training_backends/megatron/run_megatron_qwen3-235b-a22b.sh -------------------------------------------------------------------------------- /skyrl-train/examples/training_backends/megatron/run_megatron_qwen3-30b-a3b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/training_backends/megatron/run_megatron_qwen3-30b-a3b.sh -------------------------------------------------------------------------------- /skyrl-train/examples/training_backends/megatron/run_search_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/training_backends/megatron/run_search_megatron.sh -------------------------------------------------------------------------------- /skyrl-train/examples/training_backends/run_no_seq_pack.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/training_backends/run_no_seq_pack.sh -------------------------------------------------------------------------------- /skyrl-train/examples/turn_level_rewards/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/turn_level_rewards/README.md -------------------------------------------------------------------------------- /skyrl-train/examples/turn_level_rewards/gsm8k_multi_turn_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/turn_level_rewards/gsm8k_multi_turn_dataset.py -------------------------------------------------------------------------------- /skyrl-train/examples/turn_level_rewards/run_gsm8k_multi_turn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/examples/turn_level_rewards/run_gsm8k_multi_turn.sh -------------------------------------------------------------------------------- /skyrl-train/integrations/verifiers/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/integrations/verifiers/README.md -------------------------------------------------------------------------------- /skyrl-train/integrations/verifiers/entrypoints/main_verifiers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/integrations/verifiers/entrypoints/main_verifiers.py -------------------------------------------------------------------------------- /skyrl-train/integrations/verifiers/install_environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/integrations/verifiers/install_environment.py -------------------------------------------------------------------------------- /skyrl-train/integrations/verifiers/prepare_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/integrations/verifiers/prepare_dataset.py -------------------------------------------------------------------------------- /skyrl-train/integrations/verifiers/run_verifiers.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/integrations/verifiers/run_verifiers.sh -------------------------------------------------------------------------------- /skyrl-train/integrations/verifiers/verifiers_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/integrations/verifiers/verifiers_generator.py -------------------------------------------------------------------------------- /skyrl-train/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/pyproject.toml -------------------------------------------------------------------------------- /skyrl-train/scripts/full_context/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/scripts/full_context/README.md -------------------------------------------------------------------------------- /skyrl-train/scripts/full_context/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/scripts/full_context/__init__.py -------------------------------------------------------------------------------- /skyrl-train/scripts/full_context/main_full_ctx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/scripts/full_context/main_full_ctx.py -------------------------------------------------------------------------------- /skyrl-train/scripts/full_context/run_full_ctx.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/scripts/full_context/run_full_ctx.sh -------------------------------------------------------------------------------- /skyrl-train/scripts/full_context/trainer_full_ctx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/scripts/full_context/trainer_full_ctx.py -------------------------------------------------------------------------------- /skyrl-train/scripts/launch_multiple_remote_servers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/scripts/launch_multiple_remote_servers.py -------------------------------------------------------------------------------- /skyrl-train/scripts/multi_node_nccl_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/scripts/multi_node_nccl_test.py -------------------------------------------------------------------------------- /skyrl-train/skyrl-gym: -------------------------------------------------------------------------------- 1 | ../skyrl-gym/ -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/config/deepspeed_config/eval.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/config/deepspeed_config/eval.yaml -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/config/deepspeed_config/train.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/config/deepspeed_config/train.yaml -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/config/megatron_config/policy.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/config/megatron_config/policy.yaml -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/config/megatron_config/ref.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/config/megatron_config/ref.yaml -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/config/ppo_base_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/config/ppo_base_config.yaml -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/config/skyrl_gym_config/default.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/config/skyrl_gym_config/default.yaml -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/dataset/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/dataset/__init__.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/dataset/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/dataset/dataset.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/dataset/preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/dataset/preprocess.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/dataset/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/dataset/replay_buffer.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/distributed/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/distributed/deepspeed_strategy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/distributed/deepspeed_strategy.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/distributed/dispatch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/distributed/dispatch.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/distributed/fsdp_strategy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/distributed/fsdp_strategy.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/distributed/fsdp_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/distributed/fsdp_utils.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/distributed/megatron/megatron_strategy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/distributed/megatron/megatron_strategy.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/distributed/megatron/megatron_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/distributed/megatron/megatron_utils.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/distributed/megatron/model_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/distributed/megatron/model_utils.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/distributed/megatron/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/distributed/megatron/optimizer.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/distributed/strategy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/distributed/strategy.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/distributed/ulysses/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/distributed/ulysses/__init__.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/distributed/ulysses/monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/distributed/ulysses/monkey_patch.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/distributed/ulysses/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/distributed/ulysses/utils.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/distributed/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/distributed/utils.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/entrypoints/main_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/entrypoints/main_base.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/entrypoints/main_generate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/entrypoints/main_generate.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/evaluate.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/generators/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/generators/__init__.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/generators/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/generators/base.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/generators/skyrl_gym_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/generators/skyrl_gym_generator.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/generators/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/generators/utils.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/inference_engines/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/inference_engines/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/inference_engines/base.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/inference_engines/inference_engine_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/inference_engines/inference_engine_client.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/inference_engines/inference_engine_client_http_endpoint.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/inference_engines/inference_engine_client_http_endpoint.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/inference_engines/ray_wrapped_inference_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/inference_engines/ray_wrapped_inference_engine.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/inference_engines/remote_inference_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/inference_engines/remote_inference_engine.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/inference_engines/sglang/sglang_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/inference_engines/sglang/sglang_engine.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/inference_engines/sglang/sglang_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/inference_engines/sglang/sglang_server.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/inference_engines/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/inference_engines/utils.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/inference_engines/vllm/vllm_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/inference_engines/vllm/vllm_engine.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/inference_engines/vllm/vllm_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/inference_engines/vllm/vllm_server.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/models.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/trainer.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/training_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/training_batch.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/utils/__init__.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/utils/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/utils/constants.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/utils/io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/utils/io.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/utils/ppo_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/utils/ppo_utils.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/utils/profiler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/utils/profiler.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/utils/torch_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/utils/torch_utils.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/utils/tracking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/utils/tracking.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/utils/trainer_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/utils/trainer_utils.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/utils/utils.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/weights_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/weights_manager.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/workers/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/workers/deepspeed/deepspeed_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/workers/deepspeed/deepspeed_worker.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/workers/fsdp/fsdp_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/workers/fsdp/fsdp_worker.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/workers/megatron/megatron_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/workers/megatron/megatron_policy.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/workers/megatron/megatron_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/workers/megatron/megatron_worker.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/workers/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/workers/worker.py -------------------------------------------------------------------------------- /skyrl-train/skyrl_train/workers/worker_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/skyrl_train/workers/worker_utils.py -------------------------------------------------------------------------------- /skyrl-train/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/__init__.py: -------------------------------------------------------------------------------- 1 | # CPU Tests 2 | -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/algorithms/test_losses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/algorithms/test_losses.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/conftest.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/dataset/test_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/dataset/test_dataset.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/dataset/test_preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/dataset/test_preprocess.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/distributed/test_dispatch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/distributed/test_dispatch.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/distributed/test_ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/distributed/test_ulysses.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/generators/test_skyrl_gym_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/generators/test_skyrl_gym_generator.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/generators/test_skyrl_gym_generator_chat_templating.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/generators/test_skyrl_gym_generator_chat_templating.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/generators/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/generators/test_utils.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/inf_engines/test_inference_engine_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/inf_engines/test_inference_engine_client.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/inf_engines/test_route_prompts_to_engines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/inf_engines/test_route_prompts_to_engines.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/models/test_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/models/test_models.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/test_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/test_eval.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/test_generator_postprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/test_generator_postprocess.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/test_train_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/test_train_batch.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/test_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/test_trainer.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/test_trainer_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/test_trainer_utils.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/util.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/utils/test_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/utils/test_io.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/utils/test_ppo_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/utils/test_ppo_utils.py -------------------------------------------------------------------------------- /skyrl-train/tests/cpu/utils/test_torch_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/cpu/utils/test_torch_utils.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/conftest.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/gpu_ci/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/gpu_ci/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/gpu_ci/conftest.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/gpu_ci/test_engine_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/gpu_ci/test_engine_generation.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/gpu_ci/test_inference_engine_client_http_endpoint.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/gpu_ci/test_inference_engine_client_http_endpoint.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/gpu_ci/test_models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/gpu_ci/test_models.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/gpu_ci/test_save_load_checkpoint.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/gpu_ci/test_save_load_checkpoint.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/gpu_ci/test_skyrl_gym_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/gpu_ci/test_skyrl_gym_generator.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/gpu_ci/test_train_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/gpu_ci/test_train_batch.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/gpu_ci/test_trainer_full_checkpointing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/gpu_ci/test_trainer_full_checkpointing.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/gpu_ci/test_verifiers_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/gpu_ci/test_verifiers_generator.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/gpu_e2e_test/gsm8k_colocate.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/gpu_e2e_test/gsm8k_colocate.sh -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/runner.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/test_expert_parallel_inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/test_expert_parallel_inference.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/test_grpo_sp_sanity.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/test_grpo_sp_sanity.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/test_main_generate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/test_main_generate.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/test_megatron_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/test_megatron_worker.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/test_multi_node_pg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/test_multi_node_pg.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/test_policy_local_engines_e2e.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/test_policy_local_engines_e2e.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/test_ppo_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/test_ppo_train.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/test_save_load_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/test_save_load_model.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/test_skyrl_gym_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/test_skyrl_gym_generator.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/test_training_step.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/test_training_step.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/test_worker_offload.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/test_worker_offload.py -------------------------------------------------------------------------------- /skyrl-train/tests/gpu/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/tests/gpu/utils.py -------------------------------------------------------------------------------- /skyrl-train/uv.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ztcanddota/skyagent/HEAD/skyrl-train/uv.lock --------------------------------------------------------------------------------