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 low cpu speed issue (#1251)
Wenhua Cheng committed 10 months ago
90db444
Update setting of disable opt rtn (#1249)
Weiwei committed 10 months ago
cc521ca
[HPU]Export lazy mode env explicit (#1239)
Yi Liu committed 10 months ago
001d0e3
[API Change]rename fp_layers to ignore_layers (#1233)
Wenhua Cheng committed 10 months ago
0ad224c
Add FP8 dtype info to quant config (#1228)
Yi Liu committed 10 months ago
afea815
[STEP 2] refactor format and export (#1192)
Heng Guo committed 10 months ago
c244905
41a8377
Add CodeQL analysis workflow configuration (#1223)
Sun, Xuehao committed 10 months ago
8c72f5f
open source alg_ext (#1219)
Wenhua Cheng committed 10 months ago
86ae59e
[pre-commit.ci] pre-commit autoupdate (#1222)
pre-commit-ci[bot] committed 10 months ago
beb1e0c
fix torch dtype (#1217)
Wenhua Cheng committed 10 months ago
46aec78
Extend ark CI test trigger scope (#1218)
chen, suyue committed 10 months ago
ded1ea7
Update version (#1215)
Sun, Xuehao committed 10 months ago
264679c
fix calibration device issue in some scenarios (#1213)
Wenhua Cheng committed 10 months ago
8c0f01e
update diffusion args (#1210)
Wang, Mengni committed 10 months ago
cf746d4
fix scale dtype (#1207)
Wenhua Cheng committed 10 months ago
f670a25
Fix llama4 kv quant (#1205)
Wang, Mengni committed 10 months ago
cdd96a8
fix backend issue (#1209)
Wenhua Cheng committed 10 months ago
95ffb8d
remove ark support for cpu (#1206)
Wenhua Cheng committed 10 months ago
083b635
b3ec445
56ad9d8
Add FP8 KV Support for DS (#1180)
Yi Liu committed 10 months ago
d390de0
fix llama4 kv quant (#1199)
Wang, Mengni committed 10 months ago
dd8ce2e
af20202