chen 63a03ee152 [feature]2.2 custom_allreduce support cudagraph recapture (#4307) ...

* custom_allreduce support cudagraph recapture

* delete code

* add shut_down/restart default group

2025-09-29 18:14:21 +08:00

..

cpu_ops

[Code Simplification] remove cum_offsets (#3410)

2025-08-18 20:21:25 +08:00

gpu_ops

[feature]2.2 custom_allreduce support cudagraph recapture (#4307)

2025-09-29 18:14:21 +08:00

iluvatar_ops

[Iluvatar GPU] Optimze attention and moe performance (#3234)

2025-08-08 10:51:24 +08:00

third_party

[setup optimize]Support git submodule (#4033) (#4080)

2025-09-15 11:41:55 +08:00

utils

【Fix bug] w4afp8 的nblock固定为256，并且fa3的append attn 增加mask参数 (#3771) (#3835)

2025-09-03 19:36:45 +08:00

xpu_ops

[XPU] Update XPU stable xvllm and xtdk version for 2.2 & Change CI Case (#3855)

2025-09-03 19:33:06 +08:00

0001-DeepGEMM-95e81b3.patch

[feat] support fa3 backend for pd disaggregated (#2695)

2025-07-03 22:33:27 +08:00

MANIFEST.in

[LLM] First commit the llm deployment code

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

setup_ops_cpu.py

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

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

setup_ops.py

[feat] support prefix cache clearing when /clear_load_weight is called (#4091)

2025-09-16 11:11:20 +08:00