yzwu 6674131b0b [Iluvatar] Support CudaGraph and optimize flash_attn_unpadded and fused_neox_rope_embedding (#6553)

2026-03-02 14:07:17 +08:00

..

tool_parsers

…

v1

…

__init__.py

…

api_server.py

…

middleware.py

…

multi_api_server.py

[Iluvatar] Support CudaGraph and optimize flash_attn_unpadded and fused_neox_rope_embedding (#6553)

2026-03-02 14:07:17 +08:00

protocol.py

…

response_processors.py

…

run_batch.py

…

serving_chat.py

…

serving_completion.py

…

serving_embedding.py

…

serving_engine.py

…

serving_models.py

…

serving_reward.py

…

test_openai.py

…

usage_calculator.py

…

utils.py

…