cheunglei 53b3ef2e32 support tensor parallel

2025-06-15 01:31:24 +08:00

..

activation.py

init commit

2025-06-10 00:27:01 +08:00

attention.py

refactor

2025-06-11 21:12:57 +08:00

embed_head.py

support tensor parallel

2025-06-15 01:31:24 +08:00

layernorm.py

init commit

2025-06-10 00:27:01 +08:00

linear.py

support tensor parallel

2025-06-15 01:31:24 +08:00

rotary_embedding.py

init commit

2025-06-10 00:27:01 +08:00

sampler.py

fix

2025-06-10 21:25:54 +08:00