Skip to content
Arm
Git
Search or jump to…
Ctrl K
Categories
Theme: System
Sign in
Get started
armgit
/
auto-round
Public
Imported from GitHub
Fork
0
Watch
0
Star
0
PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
Python
diffusers
gguf
int4
llms
mxfp4
nvfp4
omni
quantization
rounding
sglang
transformers
vllm
vlms
Code
Commits
Issues
Pull requests
Wiki
Builds
Discussions
Projects
Insights
Search
main
291 branches · 45 tags
Go to file
t
Code
Commits on
main
update readme (#550)
Wenhua Cheng committed 1 year ago
59cf22e
Copy SHA
[critic bug]remove redundant round in dq simulation (#543)
Wenhua Cheng committed 1 year ago
c6155fd
Copy SHA
fix_quantization_config_for_inference (#542)
WeiweiZhang1 committed 1 year ago
7657640
Copy SHA
freeze pytorch & ipex version in CI (#541)
Sun, Xuehao committed 1 year ago
784273e
Copy SHA
bump version into v0.5.1 (#540)
Sun, Xuehao committed 1 year ago
336ef66
Copy SHA
fix triton multiple gpus and some other issues (#539)
Wenhua Cheng committed 1 year ago
d6d6dad
Copy SHA
bump version into v0.5.0 (#538)
Sun, Xuehao committed 1 year ago
88e6e3b
Copy SHA
fix cuda ut (#537)
Heng Guo committed 1 year ago
eee1752
Copy SHA
refine readme (#536)
WeiweiZhang1 committed 1 year ago
3f42edd
Copy SHA
update readme (#531)
Wenhua Cheng committed 1 year ago
87579ef
Copy SHA
fix inference issue (#529)
Wenhua Cheng committed 1 year ago
322ad6e
Copy SHA
fix bug of cuda ut (#532)
Heng Guo committed 1 year ago
03f3dcd
Copy SHA
update mllm readme (#530)
WeiweiZhang1 committed 1 year ago
5e18368
Copy SHA
add backend readme (#528)
Wenhua Cheng committed 1 year ago
c62cd0f
Copy SHA
fix typos, add model card link for VLMs (#527)
WeiweiZhang1 committed 1 year ago
45df79c
Copy SHA
fix light config (#526)
WeiweiZhang1 committed 1 year ago
796f332
Copy SHA
update convert_hf_to_gguf to support more models (#524)
Heng Guo committed 1 year ago
aabf1d5
Copy SHA
rm fp16 export in autoround format (#525)
Wenhua Cheng committed 1 year ago
5d82266
Copy SHA
fix examples model_dtype (#523)
WeiweiZhang1 committed 1 year ago
530bde9
Copy SHA
rename backend to packing_format in config.json (#521)
Wenhua Cheng committed 1 year ago
471dae8
Copy SHA
patch for vlm (#518)
Heng Guo committed 1 year ago
f3f017a
Copy SHA
add regex support in layer_config setting (#519)
Wenhua Cheng committed 1 year ago
d286538
Copy SHA
fix bs!=1 for gemma and MiniMax-Text-01 (#515)
Wenhua Cheng committed 1 year ago
23cd60d
Copy SHA
move gguf-dq test to cuda (#520)
Heng Guo committed 1 year ago
3774f93
Copy SHA
support for more vlms (#390)
Heng Guo committed 1 year ago
9c7a443
Copy SHA
add group_size divisible check in backend (#512)
Wenhua Cheng committed 1 year ago
f55cde9
Copy SHA
Update requirements-lib.txt (#513)
Yi Liu committed 1 year ago
c480e83
Copy SHA
fix critical bug of get_multimodal_block_names (#509)
Heng Guo committed 1 year ago
ee890b2
Copy SHA
support rtn via iters==0 (#510)
Wenhua Cheng committed 1 year ago
58ca583
Copy SHA
fix setup issue on cuda machine (#511)
Wenhua Cheng committed 1 year ago
5801ee9
Copy SHA
Newer
Older