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

6190869
fix tied weights keys bug (#1330)
Wenhua Cheng committed 10 months ago
25364d2
simplify pull_request_template.md (#1328)
Xin He committed 10 months ago
cf37d8e
57d1a8a
set predefined ignore layers (#1318)
Wenhua Cheng committed 10 months ago
7c397e1
fix low_cpu and set it to True as default (#1288)
Wenhua Cheng committed 10 months ago
f654e52
fix XPU CI hang issue (#1261)
Xin He committed 10 months ago
57af5b7
fix bug of format (#1287)
Heng Guo committed 10 months ago
5ba31b6
d8ed35a
open source delta loss (#1300)
Wenhua Cheng committed 10 months ago
587eadb
fix ignore layers regression (#1302)
Wenhua Cheng committed 10 months ago
3352a83
Remove itrex format (#1301)
Tang Kaihui committed 10 months ago
46f8860
Update unit test script (#1290)
Sun, Xuehao committed 10 months ago
8e6f337
Update version (#1282)
Sun, Xuehao committed 10 months ago
47c8aa4
auto-round-kernel installation method (#1221)
chen, suyue committed 10 months ago
ba48dd7
6e1ea9c
add permission for workflow (#1190)
chen, suyue committed 10 months ago
94db905
Update HPU CI to gaudi v1.23.0 (#1271)
Sun, Xuehao committed 10 months ago
56750e8
Fix critic bug causing GGUF to run on CPU (#1260)
Wenhua Cheng committed 10 months ago
1b7535a
update supported scheme readme (#1257)
Wenhua Cheng committed 10 months ago
6a87a65
Update nightly release workflow (#1256)
chen, suyue committed 10 months ago
583278d
Add nightly release workflow (#1255)
chen, suyue committed 10 months ago
b4ab21d
fix cuda ut fail (#1237)
Heng Guo committed 10 months ago
7a46aee