DeepSeek-V3/inference
sunndy ebd889518d
Update kernel.py
a.size(-1) : K是a的列数
a.numel//K : M是a的行数
b.size(0) 是行数,
b.size(-1)才是b的列数。
这里是求a@b。结果应该是a的行数 X b的列数。N的值应该是b.size(-1)
2025-03-03 19:38:53 +08:00
..
configs Release DeepSeek-V3 2024-12-26 19:01:57 +08:00
convert.py clarify assertion error 2025-01-28 13:16:54 +01:00
fp8_cast_bf16.py Enhance documentation and update .gitignore for model conversion scripts 2025-01-05 18:18:18 +00:00
generate.py clarify assertion error 2025-01-28 13:16:54 +01:00
kernel.py Update kernel.py 2025-03-03 19:38:53 +08:00
model.py fix scores mask 2025-02-14 20:26:45 +08:00
requirements.txt Release DeepSeek-V3 2024-12-26 19:01:57 +08:00