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

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

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

args_utils.py

custom all reduce support cuda graph (#2938)

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

config.py

custom all reduce support cuda graph (#2938)

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

engine.py

custom all reduce support cuda graph (#2938)

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

expert_service.py

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

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

kv_cache_interface.py

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

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

request.py

[Feature] Add return_token_ids, prompt_token_ids, and delete training, raw_request in request body (#2940)

2025-07-21 19:31:14 +08:00

resource_manager.py

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

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

sampling_params.py

[Feature] support min_p_sampling (#2872)

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