leideng/QCFuse / srt /layers /quantization
466 GB
2,808 files
Updated 13 days ago
Name
Size
compressed_tensors
configs
quark
__init__.py6.34 kB
xet
awq.py33.4 kB
xet
awq_triton.py12.7 kB
xet
base_config.py7.9 kB
xet
blockwise_int8.py14 kB
xet
fp8.py53.4 kB
xet
fp8_kernel.py56.2 kB
xet
fp8_utils.py29.8 kB
xet
fpgemm_fp8.py6.97 kB
xet
gptq.py39.4 kB
xet
int8_kernel.py13.1 kB
xet
int8_utils.py2.36 kB
xet
kv_cache.py3.26 kB
xet
marlin_utils.py26.6 kB
xet
marlin_utils_fp8.py12.5 kB
xet
modelopt_quant.py60.7 kB
xet
moe_wna16.py19.1 kB
xet
mxfp4.py31.8 kB
xet
mxfp4_tensor.py5.39 kB
xet
petit.py8.94 kB
xet
petit_utils.py3.25 kB
xet
qoq.py8.14 kB
xet
rocm_mxfp4_utils.py327 Bytes
xet
unquant.py16 kB
xet
utils.py18.5 kB
xet
w4afp8.py13 kB
xet
w8a8_fp8.py10.4 kB
xet
w8a8_int8.py37.5 kB
xet
Total size
466 GB
Files
2,808
Last updated
Jun 16
Pre-warmed CDN
US EU US EU

Contributors