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

[Important Change]change mxfp8 to OCP standard (#1183)
Wenhua Cheng committed 10 months ago
4d3527f
17b67e1
UT refactor for preview (#1160)
Xin He committed 10 months ago
cca98b4
Refactor module replacement (#1153)
Yi Liu committed 11 months ago
87d5580
fix llama4 ut (#1197)
Weiwei committed 11 months ago
0554a4d
Update version (#1191)
Sun, Xuehao committed 11 months ago
6fb1168
fix cuda ut fail (#1189)
Heng Guo committed 11 months ago
adc1da6
[STEP 1] refactor output formats (#1159)
Heng Guo committed 11 months ago
0dc5e9c
Enable qwen3 vl moe quant and load (#1182)
Weiwei committed 11 months ago
d193506
fix scale_dtype is None issue (#1185)
Xin He committed 11 months ago
440288f
13ba747
Enable ark CI model test (#1177)
chen, suyue committed 11 months ago
3a55a57
Fix code for llmc llama4 quantization (#1161)
Wang, Mengni committed 11 months ago
3c88b3b
fd5a172
Deprecate awq infer ut (#1171)
Weiwei committed 11 months ago
2800c3e
Fix accuracy bug in the customized dataset (#1162)
Wenhua Cheng committed 11 months ago
b53ead7
Add G2-specific `FP8_STATIC` support (#1148)
Yi Liu committed 11 months ago
547d43f
handle key not found issue (#1156)
Xin He committed 11 months ago
dd9579e
update norm bias tuning doc (#1155)
Wenhua Cheng committed 11 months ago
6723ef0
fix asym quantization issue (#1158)
Wenhua Cheng committed 11 months ago
1c23c74
Revert "[STEP 1] refact output formats" (#1157)
Heng Guo committed 11 months ago
c91b404
[STEP 1] refact output formats (#906)
Heng Guo committed 11 months ago
cf99bb3
Fix cuda test and llmc test (#1152)
Sun, Xuehao committed 11 months ago
07c9f63
add more blog in README (#1147)
Xin He committed 11 months ago
3f92963
update cd workflow (#1151)
chen, suyue committed 11 months ago
1ac2f15
746f32b
add new posts and align the format (#1125)
Xin He committed 11 months ago
32b884e
Added ark backend (#1075)
Zhenzhong Xu committed 11 months ago
2592646