Chunyuan WU 1dce6c480f [CPU] support the case where num_attention_heads or intermediate_size is not divisible by the TP size (#6771)

2025-07-03 09:51:38 -07:00

..

__init__.py

Update model_loader deps and qqq quantization deps (#2220) (#2318)

2024-12-02 23:22:13 +08:00

loader.py

support llama4 eagle3 (#6985)

2025-06-30 22:34:10 -07:00

utils.py

[FEAT] Add transformers backend support (#5929)

2025-06-03 21:05:29 -07:00

weight_utils.py

[CPU] support the case where num_attention_heads or intermediate_size is not divisible by the TP size (#6771)

2025-07-03 09:51:38 -07:00