issues
search
intel
/
neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
https://intel.github.io/neural-compressor/
Apache License 2.0
2.18k
stars
252
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
adapt transformers 4.45
#2020
changwangss
closed
1 day ago
1
Adapt transformers 4.45.1
#2019
Kaihui-intel
closed
1 day ago
0
Add transformers-like api doc
#2018
Kaihui-intel
closed
1 day ago
0
Qwen/Qwen2.5-7B-Instruct model layer_wise_quant function error
#2017
hadoop2xu
opened
1 day ago
0
Remove itrex dependency for 3x example
#2016
Kaihui-intel
opened
4 days ago
0
Update optimized model type on ipex-xpu
#2015
Kaihui-intel
closed
4 days ago
1
[Doc] Add autoround EMNLP24 paper to pub list
#2014
thuang6
closed
1 day ago
2
Update auto_round requirements for transformers example
#2013
Kaihui-intel
closed
5 days ago
0
Add vlm examples, bugfix
#2012
WeiweiZhang1
opened
5 days ago
0
add pad_to_buckets in evaluation for hpu performance
#2011
xin3he
closed
4 days ago
1
Fix xpu device set weight and bias
#2010
changwangss
closed
4 days ago
0
Fix xpu device set weight and bias.
#2009
changwangss
closed
1 week ago
0
Fix transformers rtn layer-wise quant
#2008
Kaihui-intel
closed
1 day ago
0
remove accelerate version in unit test
#2007
XuehaoSun
closed
1 week ago
0
Update model accuracy
#2006
XuehaoSun
closed
4 days ago
0
Replace FORCE_DEVICE with INC_TARGET_DEVICE [transformers]
#2005
Kaihui-intel
closed
2 weeks ago
0
For TEST
#2004
Kaihui-intel
closed
2 weeks ago
0
update docker image prune rules in CI
#2003
chensuyue
closed
2 weeks ago
0
enable auto_round format export
#2002
WeiweiZhang1
closed
2 weeks ago
0
Failed to save quantized model
#2001
lockeregg
opened
2 weeks ago
9
LLM smoothquant, how to add a customer evaluate func ?
#1999
tianylijun
closed
1 week ago
1
add repack_awq_to_optimum_format function
#1998
changwangss
closed
1 week ago
1
remove peft from installation requirement
#1997
xin3he
closed
2 weeks ago
0
smoothquant, any quant/dequant module can be found in exported quant pt model ?
#1996
tianylijun
closed
3 weeks ago
0
Add recent publications
#1995
thuang6
closed
3 weeks ago
0
Remove the save of gptq config
#1993
Kaihui-intel
closed
4 weeks ago
1
update 3x pt binary build
#1992
chensuyue
closed
1 month ago
0
update installation and ci test for 3x api
#1991
chensuyue
closed
1 month ago
0
Add `PerChannelMinMaxObserver` for PT2E
#1990
yiliu30
closed
4 weeks ago
1
Correct a typo in installation_guide.md
#1989
thuang6
closed
1 month ago
0
add INC_FORCE_DEVICE introduction
#1988
xin3he
closed
2 weeks ago
0
Support transformers-like api for woq quantization
#1987
Kaihui-intel
closed
2 weeks ago
1
add quantize, save, load function for transformers-like api
#1986
changwangss
closed
1 month ago
2
add hasattr check for torch fp8 dtype
#1985
xin3he
closed
1 month ago
1
NotImplementedError is raised in static INT8 Quantization with PT2E Backend default recipe
#1984
haitamhawa
closed
1 month ago
7
Test CI
#1983
Kaihui-intel
closed
1 month ago
1
Add woq examples
#1982
Kaihui-intel
opened
1 month ago
0
Skip some tests for torch 2.4
#1981
yiliu30
closed
1 month ago
0
how to evaluate AWQ ?
#1980
chunniunai220ml
opened
1 month ago
7
update readme for fp8
#1979
xin3he
closed
1 month ago
0
Fix UT env
#1978
XuehaoSun
closed
1 month ago
0
support gptq `true_sequential` and `quant_lm_head`
#1977
Kaihui-intel
closed
1 month ago
0
add online doc for 2.4, 2.5, 2.6, 3.0
#1976
NeoZhangJianyu
closed
1 month ago
0
fix online doc search issue
#1975
NeoZhangJianyu
closed
1 month ago
0
bump main version into v3.1
#1974
chensuyue
closed
1 month ago
0
update main page
#1973
chensuyue
closed
1 month ago
0
Quantization failed
#1972
endomorphosis
opened
1 month ago
1
Add 3.x readme
#1971
XuehaoSun
closed
1 month ago
0
Update LLM accuracy
#1970
XuehaoSun
closed
1 month ago
0
Fix broken link in docs
#1969
thuang6
closed
1 month ago
0
Next