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
Model Size Increase After PTQ
#1968
zhangxu223
closed
1 month ago
8
Add version mapping between INC and Gaudi SW Stack
#1967
thuang6
closed
1 month ago
0
remove unnecessary CI
#1966
XuehaoSun
closed
1 month ago
0
Fix `opt_125m_woq_gptq_int4_dq_ggml` issue
#1965
Kaihui-intel
closed
1 month ago
1
Cherry pick v1.17.0
#1964
xin3he
closed
1 month ago
0
Why is LayerNorm not quantized to int8 in PTQ?
#1963
zhangxu223
closed
1 month ago
3
fix welcome.html link issue
#1962
NeoZhangJianyu
closed
2 months ago
0
Bump tensorflow from 2.12 to 2.12.1 in /examples/tensorflow/nlp/large_language_models/quantization/ptq/gpt-j
#1961
dependabot[bot]
closed
2 months ago
0
Set `low_gpu_mem_usage=False` for AutoRound
#1960
Kaihui-intel
closed
2 months ago
0
fix docs link
#1959
chensuyue
closed
2 months ago
0
new results or previous results could not find all raise issues in CI model test
#1958
chensuyue
closed
2 months ago
0
update 3x torch installation
#1957
chensuyue
closed
2 months ago
0
Add docstring for auto accelerator
#1956
yiliu30
closed
2 months ago
0
replenish docstring
#1955
xin3he
closed
2 months ago
0
Fix itrex qbits nf4/int8 training core dumped issue
#1954
Kaihui-intel
closed
2 months ago
2
Fix to_json_file function in BaseConfig
#1953
yuwenzho
closed
2 months ago
1
Bump torch from 1.13.1+cpu to 2.2.0 in /examples/notebook/pytorch/alexnet_fashion_mnist/scripts
#1952
dependabot[bot]
closed
2 months ago
1
Dataset Selection for Post-Training Quantization (PTQ)
#1951
zhangxu223
closed
1 month ago
5
Update publish.yml
#1950
NeoZhangJianyu
closed
2 months ago
0
Update publish.yml
#1949
NeoZhangJianyu
closed
2 months ago
0
add ipex xpu example to 3x API
#1948
violetch24
closed
2 months ago
0
Update doc for client-usage and LWQ
#1947
yiliu30
closed
2 months ago
0
Refine Pytorch 3x Mixed Precision Example
#1946
zehao-intel
closed
2 months ago
0
Complement UT of calibration function for TF 3x API
#1945
zehao-intel
closed
2 months ago
0
Add Docstring for TF 3x API and Torch 3x Mixed Precision
#1944
zehao-intel
closed
2 months ago
1
Enable yolov5 Example for TF 3x API
#1943
zehao-intel
closed
2 months ago
0
Add read permission token per security requirement
#1942
thuang6
closed
2 months ago
0
Update AutoRound commit version
#1941
Kaihui-intel
closed
2 months ago
1
Update for API 3.0 online doc
#1940
NeoZhangJianyu
closed
2 months ago
1
[For test only] Add torch to check path
#1939
yiliu30
closed
2 months ago
2
Add docstring for WOQ&LayerWise
#1938
Kaihui-intel
closed
2 months ago
5
Add docstring for PT2E and HQQ
#1937
yiliu30
closed
2 months ago
1
add docstring for static quant and smooth quant
#1936
violetch24
closed
2 months ago
2
3.X API installation update
#1935
chensuyue
closed
2 months ago
3
Support calib_func on TF 3x API
#1934
zehao-intel
closed
2 months ago
1
remove peft version limit
#1933
chensuyue
closed
2 months ago
1
add docstring for mx quant
#1932
mengniwang95
closed
2 months ago
1
Fix unused pkgs import
#1931
Kaihui-intel
closed
2 months ago
1
Enhance load_empty_model import
#1930
Kaihui-intel
closed
2 months ago
1
update itrex ut test
#1929
chensuyue
closed
2 months ago
1
add docstring for torch.quantization and torch.utils
#1928
xin3he
closed
2 months ago
1
Add save/load for pt2e example
#1927
Kaihui-intel
closed
2 months ago
1
Integrate AutoRound v0.3 to 2x
#1926
Kaihui-intel
closed
2 months ago
3
Integrate AutoRound v0.3
#1925
Kaihui-intel
closed
2 months ago
2
Fix a typo in architecture diagram
#1924
thuang6
closed
2 months ago
1
update documentation for 3x API
#1923
chensuyue
closed
2 months ago
1
Update PyTorch Supported Matrix
#1922
xin3he
closed
2 months ago
0
Support woq Autotune
#1921
Kaihui-intel
closed
2 months ago
1
Support absorb dict for awq
#1920
Kaihui-intel
closed
2 months ago
1
Any example to quantise a text embedding model on Intel Gaudi2?
#1919
sleepingcat4
opened
2 months ago
2
Previous
Next