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

add llmc for cuda ut (#1145)
Yi Liu committed 11 months ago
2aeffe7
fix cuda ut fail (#1144)
Heng Guo committed 11 months ago
d1a4116
add low_cpu_mem_usage in cli (#1146)
Heng Guo committed 11 months ago
0b74fe1
Fix device mismatch of nvfp fuse scale (#1143)
Weiwei committed 11 months ago
ec60acf
update windows binary for alg_ext (#1142)
chen, suyue committed 11 months ago
e548171
update document for eval (#1140)
Xin He committed 11 months ago
76b100c
update readme (#1141)
Wenhua Cheng committed 11 months ago
cde5160
b38f895
f5b7a65
Remove duplicate packages (#1139)
Sun, Xuehao committed 11 months ago
b25497f
Enable load MXFP4/MXFP8 + FP8 KV (#1095)
Yi Liu committed 11 months ago
023921b
Upgrade llmc to main and add cuda UT (#1111)
Yi Liu committed 11 months ago
02aaa89
fix regression (#1135)
Xin He committed 11 months ago
8874530
Use modelscope cache in CPU UT (#1124)
Sun, Xuehao committed 11 months ago
fb43723
fix gguf extension bug (#1116)
Wenhua Cheng committed 11 months ago
bd63149
remove result to cpu (#1115)
Yi Liu committed 11 months ago
5346cb7
99e4e75
fix gguf packing device (#1105)
Heng Guo committed 11 months ago
4f64730
fix release version cuda ut fail (#1110)
Heng Guo committed 11 months ago
c9ac9a4
fix auto-scheme/alg-ext multiple devices issue (#1107)
Wenhua Cheng committed 11 months ago
3e26b0d
remove non-essential requirements (#1103)
Heng Guo committed 11 months ago
3674915
move packeding res to cpu (#1104)
Yi Liu committed 11 months ago
daa151d
refine lmhead ut (#1106)
Weiwei committed 11 months ago
814cf12
Update README.md (#1102)
Xin He committed 11 months ago
e8714e8
99bf772
fix gguf acc and oom bug when iters > 0 (#1098)
Heng Guo committed 11 months ago
09d9962