zhink 0262ef7eb3 custom all reduce support cuda graph (#2938) ...

* Support enabling cuda graph and custom all reduce at the same time, and fix the overwritten custom all reduce flag

* rename communication_op to communication

2025-07-21 22:52:03 +08:00

..

__init__.py

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

dcu_worker.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

eplb.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

experts_manager.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

gcu_model_runner.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

gcu_worker.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

gpu_model_runner.py

[Executor] Avoid OOM when start the service while Enable Chunked Prefill + CudaGraph (#2936)

2025-07-21 16:25:51 +08:00

gpu_worker.py

custom all reduce support cuda graph (#2938)

2025-07-21 22:52:03 +08:00

iluvatar_model_runner.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

iluvatar_worker.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

model_runner_base.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

output.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

utils.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

worker_base.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

worker_process.py

custom all reduce support cuda graph (#2938)

2025-07-21 22:52:03 +08:00

xpu_model_runner.py

[Feature] support min_p_sampling (#2872)

2025-07-20 23:17:59 -07:00

xpu_worker.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00