LICENSE
README.md
pyproject.toml
skyrl/__init__.py
skyrl/env_vars.py
skyrl-agent/data/browsecomp-plus.py
skyrl-agent/data/deep_research.py
skyrl-agent/data/memagent.py
skyrl-agent/data/search-r1.py
skyrl-agent/data/swe_data.py
skyrl-agent/examples/run_openai/run_openai_react.py
skyrl-agent/examples/run_openai/test_vllm_oh_demo.py
skyrl-agent/services/router_simple.py
skyrl-agent/services/test_remote_services.py
skyrl-agent/skyrl_agent/__init__.py
skyrl-agent/skyrl_agent/auto.py
skyrl-agent/skyrl_agent/agents/__init__.py
skyrl-agent/skyrl_agent/agents/base.py
skyrl-agent/skyrl_agent/agents/mapping.py
skyrl-agent/skyrl_agent/agents/oh_codeact/__init__.py
skyrl-agent/skyrl_agent/agents/oh_codeact/codeact_agent.py
skyrl-agent/skyrl_agent/agents/oh_codeact/codeact_runner.py
skyrl-agent/skyrl_agent/agents/react/__init__.py
skyrl-agent/skyrl_agent/agents/react/messages.py
skyrl-agent/skyrl_agent/agents/react/react_agent.py
skyrl-agent/skyrl_agent/agents/react/react_runner.py
skyrl-agent/skyrl_agent/config/__init__.py
skyrl-agent/skyrl_agent/config/configuration_utils.py
skyrl-agent/skyrl_agent/dispatcher/__init__.py
skyrl-agent/skyrl_agent/dispatcher/async_utils.py
skyrl-agent/skyrl_agent/dispatcher/dispatchers.py
skyrl-agent/skyrl_agent/functional/__init__.py
skyrl-agent/skyrl_agent/functional/chat_template.py
skyrl-agent/skyrl_agent/functional/function_calling.py
skyrl-agent/skyrl_agent/functional/history.py
skyrl-agent/skyrl_agent/functional/utils.py
skyrl-agent/skyrl_agent/integrations/__init__.py
skyrl-agent/skyrl_agent/integrations/base.py
skyrl-agent/skyrl_agent/integrations/openai.py
skyrl-agent/skyrl_agent/integrations/skyrl_train/__init__.py
skyrl-agent/skyrl_agent/integrations/skyrl_train/skyrl_train_backend.py
skyrl-agent/skyrl_agent/integrations/skyrl_train/skyrl_train_main.py
skyrl-agent/skyrl_agent/integrations/skyrl_train/trainer.py
skyrl-agent/skyrl_agent/integrations/tinker/__init__.py
skyrl-agent/skyrl_agent/integrations/tinker/tinker_backend.py
skyrl-agent/skyrl_agent/integrations/tinker/tinker_train.py
skyrl-agent/skyrl_agent/integrations/verl/__init__.py
skyrl-agent/skyrl_agent/integrations/verl/skyagent_async_vllm_server.py
skyrl-agent/skyrl_agent/integrations/verl/upload_utils.py
skyrl-agent/skyrl_agent/integrations/verl/verl_async_manager.py
skyrl-agent/skyrl_agent/integrations/verl/verl_backend.py
skyrl-agent/skyrl_agent/integrations/verl/verl_main_ppo.py
skyrl-agent/skyrl_agent/integrations/verl/verl_trainer.py
skyrl-agent/skyrl_agent/tasks/__init__.py
skyrl-agent/skyrl_agent/tasks/base.py
skyrl-agent/skyrl_agent/tasks/web_research_task.py
skyrl-agent/skyrl_agent/tasks/general_react/__init__.py
skyrl-agent/skyrl_agent/tasks/general_react/utils.py
skyrl-agent/skyrl_agent/tasks/swebench/__init__.py
skyrl-agent/skyrl_agent/tasks/swebench/r2e_utils.py
skyrl-agent/skyrl_agent/tasks/swebench/utils.py
skyrl-agent/skyrl_agent/tasks/swebench/scripts/tools/search.py
skyrl-agent/skyrl_agent/tasks/swebench/scripts/tools/str_replace_editor.py
skyrl-agent/skyrl_agent/tasks/verifiers/__init__.py
skyrl-agent/skyrl_agent/tasks/verifiers/naive_dapo.py
skyrl-agent/skyrl_agent/tasks/verifiers/py_functional.py
skyrl-agent/skyrl_agent/tasks/verifiers/qa.py
skyrl-agent/skyrl_agent/tasks/verifiers/coder1/__init__.py
skyrl-agent/skyrl_agent/tasks/verifiers/coder1/sandboxfusion_exec.py
skyrl-agent/skyrl_agent/tasks/verifiers/coder1/unsafe_local_exec.py
skyrl-agent/skyrl_agent/tasks/verifiers/coder1/utils.py
skyrl-agent/skyrl_agent/tasks/verifiers/prime_math/__init__.py
skyrl-agent/skyrl_agent/tasks/verifiers/prime_math/grader.py
skyrl-agent/skyrl_agent/tasks/verifiers/prime_math/math_normalize.py
skyrl-agent/skyrl_agent/tasks/verifiers/sandbox_fusion/utils.py
skyrl-agent/skyrl_agent/tasks/verifiers/torl/__init__.py
skyrl-agent/skyrl_agent/tasks/verifiers/torl/eval.py
skyrl-agent/skyrl_agent/tasks/verifiers/torl/math_verify.py
skyrl-agent/skyrl_agent/tasks/verifiers/web_search/stem_llm_judge.py
skyrl-agent/skyrl_agent/tools/__init__.py
skyrl-agent/skyrl_agent/tools/base.py
skyrl-agent/skyrl_agent/tools/cache.py
skyrl-agent/skyrl_agent/tools/em_finish.py
skyrl-agent/skyrl_agent/tools/finish.py
skyrl-agent/skyrl_agent/tools/local_search.py
skyrl-agent/skyrl_agent/tools/next_memagent.py
skyrl-agent/skyrl_agent/tools/prompt.py
skyrl-agent/skyrl_agent/tools/sandbox_fusion.py
skyrl-agent/skyrl_agent/tools/search.py
skyrl-agent/skyrl_agent/tools/search_engine.py
skyrl-agent/skyrl_agent/tools/web_browser.py
skyrl-agent/skyrl_agent/tools/youcom_search_engine.py
skyrl-gym/skyrl_gym/__init__.py
skyrl-gym/skyrl_gym/core.py
skyrl-gym/skyrl_gym/error.py
skyrl-gym/skyrl_gym/metrics.py
skyrl-gym/skyrl_gym/envs/__init__.py
skyrl-gym/skyrl_gym/envs/base_text_env.py
skyrl-gym/skyrl_gym/envs/registration.py
skyrl-gym/skyrl_gym/envs/aime/env.py
skyrl-gym/skyrl_gym/envs/aime/utils.py
skyrl-gym/skyrl_gym/envs/gsm8k/env.py
skyrl-gym/skyrl_gym/envs/gsm8k/multi_turn_env.py
skyrl-gym/skyrl_gym/envs/gsm8k/utils.py
skyrl-gym/skyrl_gym/envs/lcb/env.py
skyrl-gym/skyrl_gym/envs/lcb/livecodebench.py
skyrl-gym/skyrl_gym/envs/search/env.py
skyrl-gym/skyrl_gym/envs/search/utils.py
skyrl-gym/skyrl_gym/envs/searchcode/env.py
skyrl-gym/skyrl_gym/envs/sql/env.py
skyrl-gym/skyrl_gym/envs/sql/utils.py
skyrl-gym/skyrl_gym/tools/__init__.py
skyrl-gym/skyrl_gym/tools/core.py
skyrl-gym/skyrl_gym/tools/python.py
skyrl-gym/skyrl_gym/tools/search.py
skyrl-gym/skyrl_gym/tools/sql.py
skyrl-gym/tests/test_aime.py
skyrl-gym/tests/test_gsm8k.py
skyrl-gym/tests/test_lcb.py
skyrl-gym/tests/test_search.py
skyrl-gym/tests/test_searchcode.py
skyrl-gym/tests/test_sql.py
skyrl.egg-info/PKG-INFO
skyrl.egg-info/SOURCES.txt
skyrl.egg-info/dependency_links.txt
skyrl.egg-info/requires.txt
skyrl.egg-info/top_level.txt
skyrl/backends/__init__.py
skyrl/backends/backend.py
skyrl/backends/jax.py
skyrl/backends/renderer.py
skyrl/backends/skyrl_train_backend.py
skyrl/backends/utils.py
skyrl/backends/skyrl_train/__init__.py
skyrl/backends/skyrl_train/training_batch.py
skyrl/backends/skyrl_train/distributed/__init__.py
skyrl/backends/skyrl_train/distributed/dispatch.py
skyrl/backends/skyrl_train/distributed/fsdp_strategy.py
skyrl/backends/skyrl_train/distributed/fsdp_utils.py
skyrl/backends/skyrl_train/distributed/strategy.py
skyrl/backends/skyrl_train/distributed/utils.py
skyrl/backends/skyrl_train/distributed/megatron/megatron_strategy.py
skyrl/backends/skyrl_train/distributed/megatron/megatron_utils.py
skyrl/backends/skyrl_train/distributed/megatron/model_utils.py
skyrl/backends/skyrl_train/distributed/megatron/optimizer.py
skyrl/backends/skyrl_train/distributed/ulysses/__init__.py
skyrl/backends/skyrl_train/distributed/ulysses/monkey_patch.py
skyrl/backends/skyrl_train/distributed/ulysses/utils.py
skyrl/backends/skyrl_train/inference_engines/__init__.py
skyrl/backends/skyrl_train/inference_engines/base.py
skyrl/backends/skyrl_train/inference_engines/inference_engine_client.py
skyrl/backends/skyrl_train/inference_engines/inference_engine_client_http_endpoint.py
skyrl/backends/skyrl_train/inference_engines/ray_wrapped_inference_engine.py
skyrl/backends/skyrl_train/inference_engines/remote_inference_engine.py
skyrl/backends/skyrl_train/inference_engines/utils.py
skyrl/backends/skyrl_train/inference_engines/vllm/utils.py
skyrl/backends/skyrl_train/inference_engines/vllm/vllm_engine.py
skyrl/backends/skyrl_train/inference_engines/vllm/vllm_server.py
skyrl/backends/skyrl_train/inference_servers/__init__.py
skyrl/backends/skyrl_train/inference_servers/common.py
skyrl/backends/skyrl_train/inference_servers/new_inference_worker_wrap.py
skyrl/backends/skyrl_train/inference_servers/protocols.py
skyrl/backends/skyrl_train/inference_servers/remote_inference_client.py
skyrl/backends/skyrl_train/inference_servers/server_group.py
skyrl/backends/skyrl_train/inference_servers/server_pool.py
skyrl/backends/skyrl_train/inference_servers/setup.py
skyrl/backends/skyrl_train/inference_servers/utils.py
skyrl/backends/skyrl_train/inference_servers/vllm_router.py
skyrl/backends/skyrl_train/inference_servers/vllm_server_actor.py
skyrl/backends/skyrl_train/inference_servers/vllm_worker.py
skyrl/backends/skyrl_train/patches/gptoss/flex_attn_sink.py
skyrl/backends/skyrl_train/patches/gptoss/flex_attn_utils.py
skyrl/backends/skyrl_train/patches/gptoss/patch_transformers.py
skyrl/backends/skyrl_train/utils/__init__.py
skyrl/backends/skyrl_train/utils/off_policy_correction_utils.py
skyrl/backends/skyrl_train/utils/ppo_utils.py
skyrl/backends/skyrl_train/utils/profiler.py
skyrl/backends/skyrl_train/utils/replay_utils.py
skyrl/backends/skyrl_train/utils/torch_utils.py
skyrl/backends/skyrl_train/utils/io/io.py
skyrl/backends/skyrl_train/utils/io/s3fs.py
skyrl/backends/skyrl_train/weight_sync/__init__.py
skyrl/backends/skyrl_train/weight_sync/base.py
skyrl/backends/skyrl_train/weight_sync/broadcast_strategy.py
skyrl/backends/skyrl_train/weight_sync/cuda_ipc_strategy.py
skyrl/backends/skyrl_train/weight_sync/transfer_strategy.py
skyrl/backends/skyrl_train/weight_sync/weight_extractor.py
skyrl/backends/skyrl_train/weight_sync/weight_extractor_utils.py
skyrl/backends/skyrl_train/weight_sync/weight_loader.py
skyrl/backends/skyrl_train/workers/__init__.py
skyrl/backends/skyrl_train/workers/model_wrapper.py
skyrl/backends/skyrl_train/workers/worker.py
skyrl/backends/skyrl_train/workers/worker_dispatch.py
skyrl/backends/skyrl_train/workers/worker_utils.py
skyrl/backends/skyrl_train/workers/fsdp/fsdp_worker.py
skyrl/backends/skyrl_train/workers/megatron/megatron_model_wrapper.py
skyrl/backends/skyrl_train/workers/megatron/megatron_worker.py
skyrl/backends/skyrl_train/workers/megatron/model_bridges.py
skyrl/benchmarks/benchmark_engine.py
skyrl/benchmarks/benchmark_memory.py
skyrl/benchmarks/load_test_concurrency.py
skyrl/tinker/__init__.py
skyrl/tinker/api.py
skyrl/tinker/config.py
skyrl/tinker/db_models.py
skyrl/tinker/engine.py
skyrl/tinker/loss_fns.py
skyrl/tinker/types.py
skyrl/tinker/alembic/env.py
skyrl/tinker/extra/__init__.py
skyrl/tinker/extra/external_inference.py
skyrl/train/__init__.py
skyrl/train/evaluate.py
skyrl/train/fully_async_trainer.py
skyrl/train/main_sft.py
skyrl/train/sft_trainer.py
skyrl/train/trainer.py
skyrl/train/config/__init__.py
skyrl/train/config/config.py
skyrl/train/config/legacy.py
skyrl/train/config/sft_config.py
skyrl/train/config/utils.py
skyrl/train/dataset/__init__.py
skyrl/train/dataset/dataset.py
skyrl/train/dataset/preprocess.py
skyrl/train/dataset/replay_buffer.py
skyrl/train/entrypoints/__init__.py
skyrl/train/entrypoints/main_base.py
skyrl/train/entrypoints/main_generate.py
skyrl/train/generators/__init__.py
skyrl/train/generators/base.py
skyrl/train/generators/skyrl_gym_generator.py
skyrl/train/generators/skyrl_vlm_generator.py
skyrl/train/generators/utils.py
skyrl/train/utils/__init__.py
skyrl/train/utils/logging_utils.py
skyrl/train/utils/rate_limiter.py
skyrl/train/utils/ray_logging.py
skyrl/train/utils/tracking.py
skyrl/train/utils/trainer_utils.py
skyrl/train/utils/utils.py
skyrl/tx/__init__.py
skyrl/tx/layers/__init__.py
skyrl/tx/layers/attention.py
skyrl/tx/layers/connectors.py
skyrl/tx/layers/layernorm.py
skyrl/tx/layers/lora.py
skyrl/tx/layers/rotary_embedding.py
skyrl/tx/layers/stacked.py
skyrl/tx/layers/util.py
skyrl/tx/loaders/__init__.py
skyrl/tx/loaders/chat.py
skyrl/tx/loaders/common.py
skyrl/tx/loaders/text.py
skyrl/tx/models/__init__.py
skyrl/tx/models/configs.py
skyrl/tx/models/deepseekv3.py
skyrl/tx/models/llama3.py
skyrl/tx/models/mnist.py
skyrl/tx/models/qwen3.py
skyrl/tx/models/qwen3_5.py
skyrl/tx/models/types.py
skyrl/tx/utils/__init__.py
skyrl/tx/utils/generator.py
skyrl/tx/utils/logits_processor.py
skyrl/tx/utils/models.py
skyrl/utils/log.py
skyrl/utils/storage.py
skyrl/utils/tok.py