AIbin beec24fd89 【Inference Optimize】DeepSeek-v3 model inference performance optimization (#3455) ...

* DSK_OPT_01

* update FA3

2025-08-19 10:42:42 +08:00

..

attention

【Inference Optimize】DeepSeek-v3 model inference performance optimization (#3455)

2025-08-19 10:42:42 +08:00

backends

[GCU] Enable gcu CI (#3190)

2025-08-13 11:48:24 +08:00

moe

[V1 Loader] Support Ernie text（moe and dense） (#3110)

2025-08-14 20:25:28 +08:00

quantization

[MetaxGPU] Support FastDeploy on metax gpu (#3241)

2025-08-13 11:11:54 +08:00

sample

fix mtp_rej_topp input (#3450)

2025-08-18 16:12:42 +08:00

__init__.py

[LLM] First commit the llm deployment code

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

activation.py

[Polish Code] Remove useless notes

2025-08-14 14:04:52 +08:00

embeddings.py

[bugfix]fix blockwisefp8 and all_reduce (#3243)

2025-08-06 23:54:33 +08:00

linear.py

[V1 Loader] Support Ernie text（moe and dense） (#3110)

2025-08-14 20:25:28 +08:00

lm_head.py

fix ep lm head (#3244)

2025-08-12 15:38:28 +08:00

mtp_linear.py

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

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

normalization.py

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

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

rotary_embedding.py

[MetaxGPU] Support FastDeploy on metax gpu (#3241)

2025-08-13 11:11:54 +08:00

utils.py

Move create_parameters to __init__ in FuseMOE for CultassBackend and TritonBackend (#3148)

2025-08-08 15:55:47 +08:00