D-ARL

(★ 70)

No description available.

파일 탐색기

최종 버전 다운로드 (.zip)

- - Dockerfile.app.sglang.vllm.mcore0.12
  - Dockerfile.app.sglang.vllm.mcore0.12.deepep
  - Dockerfile.app.sglang.vllm.mcore0.13.preview
  - Dockerfile.app.vllm.mcore0.12
  - Dockerfile.app.vllm.mcore0.12.deepep
  - Dockerfile.app.vllm.mcore0.13.preview
  - Dockerfile.base
  - README.md
- - Dockerfile.app.sglang0.4.10.post2.mcore0.13
  - Dockerfile.app.sglang0.4.9.post6.mcore0.13
  - Dockerfile.app.vllm.mcore0.13
  - Dockerfile.app.vllm.mcore0.15
  - Dockerfile.base.torch2.7.1
  - README.md
- - Dockerfile.app.sglang.mcore0.12
  - Dockerfile.app.sglang.mcore0.13.preview
  - Dockerfile.base
  - README.md
- - Dockerfile.app.sglang.megatron
  - Dockerfile.base
  - README.md
- - Dockerfile.app.sglang
  - Dockerfile.base
  - Dockerfile.vllm011.mcore_gpt-oss
- Apptainerfile.rocm
- Dockerfile.extention.awsefa
- Dockerfile.ngc.vllm
- Dockerfile.ngc.vllm0.8
- Dockerfile.ngc.vllm0.8.sagemaker
- Dockerfile.rocm
- Dockerfile.rocm7
- Dockerfile.rocm_verl-0.3.0.post1
- Dockerfile.rocm_verl-0.4.1
- Dockerfile.sglang
- Dockerfile.vemlp.vllm.te
- Dockerfile.vllm.sglang.megatron.deepseek
- README.md
- - custom.css
  - logo.png
- - agent_loop.rst
  - checkpoint.rst
  - dpo_extension.rst
  - fsdp_extension.rst
  - fully_async.md
  - megatron_extension.rst
  - one_step_off.md
  - placement.rst
  - ppo_lora.rst
  - reward_loop.rst
  - rollout_is.md
  - rollout_skip.rst
  - rollout_trace.rst
  - rope.rst
- - baseline.md
  - collabllm.md
  - dapo.md
  - entropy.md
  - gpg.md
  - grpo.md
  - opo.md
  - ppo.md
  - spin.md
  - sppo.md
- - amd_build_dockerfile_page.rst
  - amd_vllm_page.rst
- - data.rst
  - single_controller.rst
  - trainer.rst
  - utils.rst
- - ascend_profiling_en.rst
  - ascend_profiling_zh.rst
  - ascend_quick_start.rst
  - ascend_sglang_quick_start.rst
- - transfer_queue.md
- - config.rst
  - gsm8k_example.rst
  - multi_modal_example.rst
  - ppo_code_architecture.rst
  - sandbox_fusion_example.rst
  - skypilot_examples.rst
- - faq.rst
- - darl_page-01.png
  - darl_page-02.png
- - device_tuning.rst
  - dpsk.md
  - nsight_profiling.md
  - perf_tuning.rst
  - verl_profiler_system.md
- - prepare_data.rst
  - reward_function.rst
- - interaction_system.rst
  - multiturn.rst
  - sandbox_fusion.rst
  - search_tool_example.rst
- - agentic_rl.rst
  - install.rst
  - more_resources.rst
  - multinode.rst
  - quickstart.rst
  - ray_debug_tutorial.rst
- - fsdp_workers.rst
  - megatron_workers.rst
  - model_engine.rst
  - ray_trainer.rst
  - sglang_worker.rst
- conf.py
- hybrid_flow.rst
- index.rst
- Makefile
- README.md
- README_vllm0.7.md
- README_vllm0.8.md
- requirements-docs.txt
- single_controller.rst
- - aime2024.py
  - aime2024_multiturn_w_tool.py
  - aime2025.py
  - countdown.py
  - dapo_multiturn_w_tool.py
  - full_hh_rlhf.py
  - geo3k.py
  - geo3k_multiturn_w_tool.py
  - gsm8k.py
  - gsm8k_multiturn_sft.py
  - gsm8k_multiturn_w_interaction.py
  - gsm8k_multiturn_w_tool.py
  - gsm8k_tool_agent_loop.py
  - hellaswag.py
  - ifeval.py
  - math500.py
  - math_lighteval.py
  - mmlu.py
  - multiturn.py
  - preprocess_search_r1_dataset.py
  - r1.py
- - run_deepseek7b_mutli_node.sh
  - run_deepseek_v2_lite_math.sh
- - README.md
  - run_qwen2_5-7b_math.sh
  - test_dapo_7b_math.sh
  - test_dapo_qwen3_30b_math.sh
- - gpg.md
  - run_qwen2-7b_math.sh
  - run_qwen2-7b_math_megatron.sh
- - README.md
  - run_deepseek671b_math_megatron_80gb.sh
  - run_deepseek671b_math_megatron_96gb.sh
  - run_deepseek7b_llm.sh
  - run_deepseek7b_llm_math.sh
  - run_deepseek7b_llm_math_megatron.sh
  - run_deepseek7b_llm_seq_balance.sh
  - run_glm41v_9b.sh
  - run_gptoss_20b.sh
  - run_minicpmo2_6.sh
  - run_mistral13b_skyworkrm_hhrlhf.sh
  - run_moonlight16b_math_megatron.sh
  - run_qwen2-7b.sh
  - run_qwen2-7b_math.sh
  - run_qwen2-7b_math_megatron.sh
  - run_qwen2-7b_seq_balance.sh
  - run_qwen2-7b_seq_balance_math_megatron.sh
  - run_qwen2-7b_sgl_megatron.sh
  - run_qwen2_5-3b_gsm8k_grpo_lora.sh
  - run_qwen2_5-7b_math_megatron_diff_tp.sh
  - run_qwen2_5_32b_grpo_npu.sh
  - run_qwen2_5_7b_grpo_discrete_prof_npu.sh
  - run_qwen2_5_7b_grpo_e2e_prof_npu.sh
  - run_qwen2_5_7b_grpo_npu.sh
  - run_qwen2_5_vl-7b-megatron.sh
  - run_qwen2_5_vl-7b-sglang.sh
  - run_qwen2_5_vl-7b.sh
  - run_qwen2_5_vl-7b_freeze_vision.sh
  - run_qwen2_5_vl-7b_lora.sh
  - run_qwen2_5_vl-7b_seq_balance.sh
  - run_qwen2_5_vl_32b_npu.sh
  - run_qwen2_5_vl_3b_npu.sh
  - run_qwen2_5_vl_7b_npu.sh
  - run_qwen3-235b_megatron_96gb.sh
  - run_qwen3-32b_npu.sh
  - run_qwen3-8b.sh
  - run_qwen3-8b_npu.sh
  - run_qwen3_8b_grpo_sglang_1k_spmd_npu.sh
  - run_qwen3_8b_grpo_sglang_32k_spmd_npu.sh
  - run_qwen3_vl-235b-megatron.sh
  - run_qwen3_vl-30b-megatron.sh
  - run_qwen3moe-30b_megatron_96gb.sh
  - run_seed_oss_36b.sh
- - README.md
  - run_deepseek7b_llm.sh
  - run_deepseek7b_llm_modelscope.sh
  - run_deepseek7b_llm_pfppo.sh
  - run_deepseek7b_llm_sandbox_fusion.sh
  - run_deepseek7b_llm_sp2.sh
  - run_deepseek_full_hh_rlhf.sh
  - run_deepseek_math_gsm8k_megatron.sh
  - run_deepseek_math_gsm8k_megatron_nsys.sh
  - run_gemma.sh
  - run_moonlight16b_a3b_gsm8k_megatron.sh
  - run_qwen1.5_moe_a2.7b-gsm8k_megatron.sh
  - run_qwen2-7b_math_gsm8k_megatron.sh
  - run_qwen2-7b_rm.sh
  - run_qwen2-7b_rm_seq_balance.sh
  - run_qwen2-7b_rm_seq_balance_fused_kernels.sh
  - run_qwen2-7b_rm_seq_balance_nsys.sh
  - run_qwen2-7b_seq_balance.sh
  - run_qwen2-7b_sglang_seq_balance.sh
  - run_qwen2.5-32b.sh
  - run_qwen3-8b_npu.sh
- - tutorial.ipynb
- - run_qwen2-7b_math_rf.sh
  - run_qwen2-7b_math_rf_baseline.sh
- - run_qwen2.5-3b_seq_balance.sh
  - run_qwen2.5-7b_seq_balance.sh
- - run_qwen2-7b.sh
- - README.md
  - run_with_rollout_is.sh
- - README.md
  - run_qwen0.5b_gsm8k_multiturn_curriculum.sh
  - run_qwen2.5-0.5b_gsm8k_multiturn_w_interaction.sh
  - run_qwen2.5-3b_gsm8k_multiturn.sh
  - run_qwen2.5-3b_gsm8k_multiturn_4xgpu.sh
  - run_qwen2.5-3b_gsm8k_multiturn_4xgpu_server.sh
  - run_qwen2.5-3b_gsm8k_multiturn_server.sh
  - run_qwen2.5-3b_gsm8k_multiturn_vllm_fsdp.sh
  - run_qwen2.5-3b_gsm8k_tool_agent_mlflow.sh
  - run_qwen2.5-3b_megatron_gsm8k_multiturn.sh
  - run_qwen3-4b_gsm8k_multiturn.sh
  - run_qwen3_4b_dapo_multiturn.sh
- - README.md
  - verl-grpo.yaml
  - verl-multiturn-tools.yaml
  - verl-ppo.yaml
- - ray_on_slurm.slurm
- - main_ppo_split.py
  - README.md
  - run_deepseek7b_llm.sh
  - split_monkey_patch.py
- - distributed_util.py
  - fsdp_workers.py
  - main_ppo.py
  - megatron_workers.py
  - ray_trainer.py
  - ray_trainer_wip.py
  - sglang_sharding_manager.py
  - utils.py
  - vllm_sharding_manager.py
- - distributed_util.py
  - fsdp_workers.py
  - main_ppo.py
  - megatron_workers.py
  - ray_trainer.py
  - ray_trainer_wip.py
  - README.md
  - utils.py
- __init__.py
- converter_hf_to_mcore.py
- diagnose.py
- generate_trainer_config.sh
- init_random_model.py
- install_vllm_sglang_mcore.sh
- legacy_model_merger.py
- print_cfg.py
- rollout_viewer.py
- verl_deps.sh
- one_step_off_grpo_1.7b_gsm8k_fsdp2_1_1_replay_4_async.sh
- one_step_off_grpo_1.7b_gsm8k_fsdp2_1_1_replay_4_decoupled.sh
- one_step_off_grpo_1.7b_gsm8k_fsdp2_1_1_replay_4_pmis_sg.sh
- one_step_off_grpo_4b_gsm8k_fsdp2_1_1_replay_4_async.sh
- one_step_off_grpo_4b_gsm8k_fsdp2_1_1_replay_4_decoupled.sh
- one_step_off_grpo_4b_gsm8k_fsdp2_1_1_replay_4_pmis_sg.sh
- ppo_qwen3_1.7b_gsm8k_async_decoupled.sh
- ppo_qwen3_1.7b_gsm8k_async_truncted.sh
- run.sh
- - __init__.py
  - test_gsm8k_interaction.py
  - test_interaction_registry.py
- - test_engine.py
  - test_transformer.py
  - test_transformers_ulysses.py
- - __init__.py
  - test_auto_padding_on_cpu.py
  - test_colocated_workers.py
  - test_colocated_workers_fused.py
  - test_data_transfer.py
  - test_decorator_on_cpu.py
  - test_device_mesh_register.py
  - test_driverfunc_to_worker.py
  - test_fused_workers_on_cpu.py
  - test_high_level_scheduling_api.py
  - test_nested_worker.py
  - test_ray_collectives.py
  - test_ray_local_envs_on_cpu.py
  - test_ray_utils_on_cpu.py
  - test_rvdz.py
  - test_worker_group_basics.py
  - test_worker_group_torch.py
- - README.md
  - run_all.sh
  - test_fsdp_ckpt.py
  - test_mcore_config_converter.py
  - test_tensor_dict.py
- - __init__.py
  - check_custom_rwd_fn.py
  - check_results.py
  - README.md
  - run_dapo.sh
  - run_fully_async_policy.sh
  - run_genrm_remote.sh
  - run_geo3k_fsdp_sgl_multiturn_w_tool.sh
  - run_grpo_lora_with_merge.sh
  - run_gsm8k_fsdp_sgl_multiturn_sf_tool.sh
  - run_gsm8k_fsdp_sgl_multiturn_w_tool.sh
  - run_one_step_off_policy.sh
  - run_ppo_trainer_megatron.sh
  - run_prime.sh
  - run_r1_distill_qwen_aime24_eval.sh
  - run_spin.sh
  - run_sppo.sh
  - run_test.sh
- - run_qwen2_5_05b_dapo.sh
  - run_qwen2_5_05b_grpo.sh
  - run_qwen2_5_05b_grpo_mindspeed.sh
  - run_qwen2_5_05b_sft_peft_sp2.sh
  - run_qwen2_5_vl_3b_npu.sh
  - run_qwen3_06b_ppo.sh
- - check_api_docs.py
  - check_dataproto_usage.py
  - check_device_api_usage.py
  - check_docs_time_info.py
  - check_docstrings.py
  - check_license.py
  - check_pr_description.py
  - check_pr_title.py
  - test_config_docs.py
  - test_import.py
  - type_coverage_check.py
  - validate_imported_docs.py
  - validate_structure.py
- - README.md
  - test_memory_buffers.py
- - __init__.py
- - _test_module.py
  - test_activation_offload.py
  - test_config_on_cpu.py
  - test_flops_counter.py
  - test_fs_on_cpu.py
  - test_groupwise.py
  - test_import_utils_on_cpu.py
  - test_linear_cross_entropy.py
  - test_mlflow_key_sanitization.py
  - test_model_on_cpu.py
  - test_nvtx_profile.py
  - test_rollout_skip_on_cpu.py
  - test_rollout_trace_on_cpu.py
  - test_seqlen_balancing.py
  - test_special_linear_cross_entropy_tp.py
  - test_special_mstx_profile.py
  - test_temp_env_on_cpu.py
  - test_timeout_decorator_cpu.py
  - test_torch_functional.py
- - test_fsdp_workers.py
- __init__.py
- kill_github_tests.sh
- README.md
- test_base_config_on_cpu.py
- test_protocol_on_cpu.py
- test_protocol_v2_on_cpu.py
- - __init__.py
- - __init__.py
  - base.py
  - gsm8k_interaction.py
  - weather_interaction.py
- - __init__.py
  - __main__.py
  - base_model_merger.py
  - fsdp_model_merger.py
  - megatron_model_merger.py
- - __init__.py
  - README.md
  - registry.py
  - weight_loader_registry.py
- - __init__.py
- - __init__.py
- - __init__.py
  - base_tool.py
  - geo3k_tool.py
  - gsm8k_tool.py
  - image_zoom_in_tool.py
  - mcp_base_tool.py
  - mcp_search_tool.py
  - sandbox_fusion_tools.py
  - schemas.py
  - search_tool.py
- - __init__.py
  - constants_ppo.py
  - fsdp_sft_trainer.py
  - main_eval.py
  - main_generation.py
  - main_generation_server.py
  - main_ppo.py
  - runtime_env.yaml
  - sft_trainer.py
- - __init__.py
  - activation_offload.py
  - attention_utils.py
  - chat_template.py
  - config.py
  - device.py
  - distributed.py
  - flops_counter.py
  - fs.py
  - fsdp_utils.py
  - groupwise.py
  - hdfs_io.py
  - import_utils.py
  - logging_utils.py
  - megatron_utils.py
  - memory_buffer.py
  - memory_utils.py
  - model.py
  - net_utils.py
  - npu_utils.py
  - py_functional.py
  - ray_utils.py
  - rollout_skip.py
  - rollout_trace.py
  - seqlen_balancing.py
  - tensordict_utils.py
  - tokenizer.py
  - torch_dtypes.py
  - torch_functional.py
  - tracking.py
  - transferqueue_utils.py
  - transformers_compat.py
  - ulysses.py
- - version
- - __init__.py
  - fsdp_workers.py
  - megatron_workers.py
- __init__.py
- base_config.py
- protocol.py
- py.typed
LICENSE
Notice.txt
ppo_test.sh
pyproject.toml
README.md
requirements-cuda.txt
requirements-npu.txt
requirements.txt
requirements_sglang.txt
requirements_transferqueue.txt
setup.py

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

D-ARL

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

D-ARL

파일 탐색기

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README