Skip to content

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度

Commits on main

fix gguf block-wise issue (#664)
Wenhua Cheng committed 1 year ago
313f436
fix bug of block-wise quant imatrix (#663)
Heng Guo committed 1 year ago
5d68aeb
support vlm models for gguf format
Heng Guo committed 1 year ago
a2f3f01
fix bug of q4_0 and q5_0 at iters==0 (#658)
Heng Guo committed 1 year ago
750a5c1
fix some issues (#655)
Wenhua Cheng committed 1 year ago
2f22e29
speedup mxfp tuning and fix nvfp bug (#647)
Wenhua Cheng committed 1 year ago
fddcb5d
35cf154
[W4A8]Fix Packing (#648)
Yi Liu committed 1 year ago
a5fa835
fix norm_bias_tuning (#639)
Wenhua Cheng committed 1 year ago
28b01fe
support llmcompressor format (#646)
Xin He committed 1 year ago
bba62c2
[BUG FIX] fix bug of deepseek gguf:q*k (#637)
Heng Guo committed 1 year ago
ba5e35c
refine gguf rtn algorithm and fix bugs (#630)
Wenhua Cheng committed 1 year ago
ef6413b
fix vlm hf config loading issue (#624)
Weiwei committed 1 year ago
5149390
fix not using imatrix for gguf at rtn mode (#623)
Wenhua Cheng committed 1 year ago
5181fa0
refine_doc_0624 (#619)
Weiwei committed 1 year ago
b6d2438
fix bug of q5_k_s w/ imatrix (#620)
Heng Guo committed 1 year ago
3bbddfc
FP8 WOQ export (#617)
Wenhua Cheng committed 1 year ago
efff6ca
fix double quant sym bug (#616)
Wenhua Cheng committed 1 year ago
21ecd8b
support customized mixed bits for gguf (#615)
Wenhua Cheng committed 1 year ago
e06bdbc
fix gguf packing bug and moe regression (#614)
Wenhua Cheng committed 1 year ago
7d18ddb
mv some checkers (#611)
Wenhua Cheng committed 1 year ago
c484bc8
fix gguf bug (#610)
Wenhua Cheng committed 1 year ago
40d99f2
fix vlm uttest path error (#601)
Weiwei committed 1 year ago
9ff62af
support for q4_k_m (#596)
Heng Guo committed 1 year ago
f3fca30