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

* DSK_OPT_01

* update FA3

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

..

graph_optimization

[Excutor] Change cudagraph hashkey from batch size to num_tokens (#3454)

2025-08-18 16:16:48 +08:00

guided_decoding

Unify server-side and model-side Config (Part3) (#3047)

2025-07-29 17:07:44 +08:00

layers

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

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

model_loader

[feat]add fast_weights_iterator (#3258)

2025-08-07 22:36:46 +08:00

models

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

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

ops

fix cpu __ini__.py (#3448)

2025-08-17 12:38:54 +08:00

__init__.py

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

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

forward_meta.py

[Excutor] Increase buffer size to prevent address corruption; add forward metadata debug tool (#3404)

2025-08-18 16:14:09 +08:00

load_weight_utils.py

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

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

pre_and_post_process.py

[Code Simplification] remove cum_offsets (#3410)

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