xiaoxiaohehe001 5223065d59 support mm mtp (#4013)

2025-09-09 13:55:45 +08:00

..

ernie4_5_vl

support mm mtp (#4013)

2025-09-09 13:55:45 +08:00

__init__.py

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

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

deepseek_v3.py

[Feature] Deepseekv3 supports cudagraph (#3041)

2025-07-28 17:12:54 +08:00

ernie4_5_moe.py

support w4afp8 EP inference (#3382)

2025-08-13 21:41:34 +08:00

ernie4_5_mtp.py

[Feature][MTP]Support new mtp (#3656)

2025-08-27 19:38:26 +08:00

model_base.py

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

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

qwen2.py

[Model] Provide clearer error for missing KV cache quantization scales (#3007)

2025-07-24 20:15:00 +08:00

qwen3.py

[Model] Provide clearer error for missing KV cache quantization scales (#3007)

2025-07-24 20:15:00 +08:00

qwen3moe.py

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

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

tp_utils.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