issues
search
OpenGVLab
/
OmniQuant
[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
MIT License
626
stars
49
forks
source link
[WIP][quantize] add gptq post-quantization
#58
Open
xingchensong
opened
6 months ago
xingchensong
commented
6 months ago
TODO
[x] training works
[ ] benchmark
TODO