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
Support PT2E save and load
#1918
Kaihui-intel
closed
2 months ago
1
fix CI docker container clean up issue
#1917
chensuyue
closed
2 months ago
1
Support xpu for ipex static quant
#1916
violetch24
closed
2 months ago
1
[For Review Only] Release Notes for v3.0
#1915
thuang6
closed
1 month ago
1
Add doc for client usage
#1914
yiliu30
closed
2 months ago
1
Add `save`/`load` support for HQQ
#1913
yiliu30
closed
2 months ago
1
update Gaudi CI baseline artifacts name
#1912
chensuyue
closed
2 months ago
1
implement TorchBaseConfig
#1911
xin3he
closed
2 months ago
1
Add export support for TEQ
#1910
yiliu30
closed
2 months ago
1
support habana fp8 test in CI
#1909
chensuyue
closed
2 months ago
1
bump version into v3.0
#1908
chensuyue
closed
2 months ago
1
Error in fp8 quantization: Invalid scale factor : 1.70e+06, make sure the scale is not larger than : 6.55e+04
#1907
yyChen233
opened
2 months ago
0
update fp4_e2m1 mapping list
#1906
changwangss
closed
2 months ago
1
Add docstring for `common` module
#1905
yiliu30
closed
2 months ago
1
Get default config based on the auto-detect CPU type
#1904
yiliu30
closed
2 months ago
1
remove neural insight CI
#1903
XuehaoSun
closed
2 months ago
1
example update for 3.x ipex sq
#1902
violetch24
closed
2 months ago
1
Update Examples for TF 3x API
#1901
zehao-intel
closed
2 months ago
1
Remove 1x docs
#1900
yiliu30
closed
2 months ago
1
add some new features for layer-wise quant
#1899
n1ck-guo
closed
2 months ago
2
remove pytorch eager mode model test
#1898
chensuyue
closed
3 months ago
1
Remove debug code.
#1897
changwangss
closed
3 months ago
1
temp fix nas deps issue
#1896
chensuyue
closed
3 months ago
1
Port auto-detect absorb layers for TEQ
#1895
yiliu30
closed
2 months ago
2
[3x] support automatic host2device on RTN and GPTQ
#1894
xin3he
closed
3 months ago
1
[pre-commit.ci] pre-commit autoupdate
#1893
pre-commit-ci[bot]
closed
2 months ago
1
fix bf16 symbolic_trace bug
#1892
xin3he
closed
2 months ago
1
FP4 encoding related
#1891
Tiantian-Han
opened
3 months ago
0
Port auto-detect absorbs layers for TEQ
#1890
yiliu30
closed
3 months ago
1
PTQ with IPEX backend and XPU device is not working
#1889
paguilomanas
opened
3 months ago
3
Refine HQQ UTs
#1888
yiliu30
closed
3 months ago
1
add SDXL model example to INC 3.x
#1887
violetch24
closed
2 months ago
1
Remove Gelu Fusion for TF Newapi
#1886
zehao-intel
closed
3 months ago
1
Update the Gaudi container example in the README and fix a typo
#1885
dmsuehir
closed
3 months ago
0
implement `incbench` command for ease-of-use benchmark
#1884
xin3he
closed
2 months ago
5
Support LayerWise for RTN/GPTQ
#1883
Kaihui-intel
closed
2 months ago
1
Update Example for Pytorch 3x Mixed Precision
#1882
zehao-intel
closed
2 months ago
2
support quant_lm_head arg in all WOQ configs
#1881
xin3he
closed
3 months ago
1
Support xpu device for 3.x ipex static
#1880
violetch24
closed
2 months ago
2
Fix sql injection for Neural Solution gRPC
#1879
Kaihui-intel
closed
3 months ago
1
Remove `.coverage`
#1878
yiliu30
closed
3 months ago
1
Enhance 3.x torch WOQ load
#1877
yuwenzho
closed
2 months ago
3
Add op statistics dump for woq
#1876
Kaihui-intel
closed
3 months ago
1
Enhance autotune to return the best `q_model` directly
#1875
yiliu30
closed
3 months ago
1
Limit numpy versions
#1874
XuehaoSun
closed
3 months ago
1
Fix GPTQ layers match
#1873
Kaihui-intel
closed
3 months ago
1
Remove deprecated modules
#1872
chensuyue
closed
2 months ago
2
update v2.6 release readme
#1871
chensuyue
closed
3 months ago
1
Add `set_local` support for static quant with pt2e
#1870
yiliu30
closed
3 months ago
2
Update SQ/WOQ status
#1869
XuehaoSun
closed
3 months ago
1
Previous
Next