gaoziyuan fbf0e9d2aa fix mem boom in ep (#3852)

2025-09-04 10:38:34 +08:00

..

attention

【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

backends

enable dcu ci (#3402)

2025-08-29 10:23:08 +08:00

moe

【BugFix】add moe noaux_tc tatics in trition backend (#3821)

2025-09-03 13:28:44 +08:00

quantization

[FIX]Fix Machete compile via ENABLE_MACHETE (#3727)

2025-08-30 17:50:17 +08:00

sample

…

__init__.py

…

activation.py

…

embeddings.py

…

linear.py

[v1loader]Reduce EB300B model loading time (#3700) (#3810)

2025-09-03 10:14:31 +08:00

lm_head.py

…

mtp_linear.py

support tmp (#3675)

2025-08-28 19:42:32 +08:00

normalization.py

…

rotary_embedding.py

[Model]support qwen2_5_vl (#3557)

2025-08-29 18:28:39 +08:00

utils.py

fix mem boom in ep (#3852)

2025-09-04 10:38:34 +08:00