auto-round
Integrate RTN quantization into GGUF packing to enhance robustness
#644
Merged
Merged
Integrate RTN quantization into GGUF packing to enhance robustness #644
wenhuach21
merged
10 commits into
main
from
hengguo/gguf_update_0704
support for gguf packing immediatly
a7c8b177
Merge branch 'main' into hengguo/gguf_update_0704
f33e6113
fix
3d6587d4
if only export gguf, using gguf-packing instead of rtn
37059d4b
wenhuach21
changed the title
wenhuach21
changed the title
fix make_q3_quants
1ed8f5ca
support for llama4
b37d270b
wenhuach21
commented
on 2025-07-07
wenhuach21
commented
on 2025-07-07
sym convert.py
ab62157a
![pre-commit-ci[bot]](https://avatars.githubusercontent.com/in/68672?v=4&s=60)
[pre-commit.ci] auto fixes from pre-commit.com hooks
36dc69fb
code scan
bf1c93b7
fix
17c2c3b3
wenhuach21
approved these changes
on 2025-07-09
Login to write a write a comment.
Login via GitHub