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

Enhance llmc CI on XPU (#1483)
chen, suyue committed 6 months ago
19b3c48
add small zimage test and fix bug (#1734)
Xin He committed 6 months ago
46b2991
85a6192
fix gemma3 gguf ut fail (#1735)
Heng Guo committed 7 months ago
98db0b3
Create model_support_request.yml (#1738)
Xin He committed 7 months ago
71f7946
Update pull_request_template.md (#1727)
Xin He committed 7 months ago
3837fc3
Support new model Qwen/Qwen3.6-35B-A3B (#1705)
Liang Lv committed 7 months ago
2dda035
refine int4 doc (#1720)
Wenhua Cheng committed 7 months ago
5b6f7ea
8428b98
add support for gemma4 model (#1655)
Heng Guo committed 7 months ago
55977e7
Update gaudi-docker to v1.24.0 & fix CUDA UT (#1708)
Sun, Xuehao committed 7 months ago
8d78450
update mtp quant for special cases (#1691)
Xin He committed 7 months ago
89769e8
rename scheme INT8_W8A8 to INT8 (#1687)
Huang, Tai committed 7 months ago
6a3bb90
693e4bd
Add Claude skills for AutoRound (#1686)
Liang Lv committed 7 months ago
4abe406
Enable low_cpu_mem_usage for mxfp/nvfp (#1648)
Tang Kaihui committed 7 months ago
8d7bb84
a4dee98
d5a0097
fp8_block bug fix (#1693)
Wang, Mengni committed 7 months ago
4210180
Support MXINT4 scheme (#1666)
Wang, Mengni committed 7 months ago
c817d49