Xingkai Yu 8710ec2ecb require model-parallel in convert.py 1 year ago
..
configs 4c2fdb8f55 Release DeepSeek-V3 1 year ago
convert.py 8710ec2ecb require model-parallel in convert.py 1 year ago
fp8_cast_bf16.py 8f1c9488b5 handle missing scale_inv_name (#2) 1 year ago
generate.py 4c2fdb8f55 Release DeepSeek-V3 1 year ago
kernel.py 4c2fdb8f55 Release DeepSeek-V3 1 year ago
model.py 4c2fdb8f55 Release DeepSeek-V3 1 year ago
requirements.txt 4c2fdb8f55 Release DeepSeek-V3 1 year ago