AIbin a7392a0ff9 【Inference Optimize】DeepSeek-V3-model MLA Optimize (#3886) ...

* support MLA chunk_size auto search & cuda_graph

2025-09-11 10:46:09 +08:00

..

attention

【Inference Optimize】DeepSeek-V3-model MLA Optimize (#3886)

2025-09-11 10:46:09 +08:00

backends

fix typos (#3684)

2025-09-01 17:50:17 +08:00

moe

[BugFix] Fix the abnormal memory usage caused by shape errors in the triton moe backend (#4026)

2025-09-09 20:05:54 -07:00

quantization

support v1 loader for machete (#3999)

2025-09-10 10:21:33 +08:00

sample

[Feature] mm and thinking model support structred output (#2749)

2025-09-02 16:21:09 +08:00

__init__.py

…

activation.py

[Polish Code] Remove useless notes

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

embeddings.py

[Feature] ernie4_5_vl_moe support huggingface safetensor loading (#3750)

2025-09-03 02:58:59 -07:00

linear.py

【Inference Optimize】Update MergedReplicatedLinear for DSK qkv_a_proj_with_mqa. (#3673)

2025-09-04 21:16:05 -07:00

lm_head.py

[Precision] Support lm_head layer running in float32 (#3597)

2025-08-27 11:34:53 +08:00

mtp_linear.py

support tmp (#3675)

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

normalization.py

adaptive rms_norm's dtype (#3617)

2025-08-26 15:29:15 +08:00

rotary_embedding.py

[Feature] Support zai-org/GLM-4.5-Air BF16 model (#3928)

2025-09-10 19:36:10 +08:00

utils.py

fix mem boom in ep (#3854)

2025-09-05 11:48:21 +08:00