Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
53 commits
Select commit Hold shift + click to select a range
1a1c80a
support pydocstyle check (#151)
chensuyue Nov 25, 2022
03cceb6
Fix Time_series_LSTM tuning issue (#163)
lvliang-intel Nov 25, 2022
54af942
Enable dilated contraction fusion for ITEX (#146)
lvliang-intel Nov 25, 2022
1ae2f36
Enable QDQ-adapted _QuantizedFusedBatchNorm+LeakyRelu fusion (#160)
ChendaLi-Intel Nov 25, 2022
7bcc400
fix pylint issue (#169)
chensuyue Nov 25, 2022
2d0e453
fix ipex quantization (#168)
changwangss Nov 25, 2022
f736360
Fix Model-Test pipeline status (#167)
XuehaoSun Nov 25, 2022
791b0e2
Improved new API (#142)
PenghuiCheng Nov 25, 2022
83b56a6
IO docs refine (#135)
WenjiaoYue Nov 25, 2022
d7c363c
Enable _MklFusedBatchMatMulV2 BF16 conversion (#147)
ChendaLi-Intel Nov 25, 2022
a33adc2
modify IO style (#170)
WenjiaoYue Nov 25, 2022
77c38ca
feat(strategy): add optimization level 0
yiliu30 Nov 21, 2022
0b69174
feat(st): update compare logic
yiliu30 Nov 22, 2022
8020881
feat(st): update best model based on perf and acc
yiliu30 Nov 23, 2022
aedf02c
feat(st): add optimization_level
yiliu30 Nov 29, 2022
70a724d
fixed some bugs
yiliu30 Nov 30, 2022
ce4422e
update the op queue
yiliu30 Dec 1, 2022
61f07f7
add optype-wise conversion
yiliu30 Dec 1, 2022
40d907c
add one by one conversion
yiliu30 Dec 1, 2022
84e421e
WA for save q model
yiliu30 Dec 2, 2022
c8207f9
fix some bugs
yiliu30 Dec 2, 2022
9ee9203
remove some comments
yiliu30 Dec 5, 2022
f9cf333
update the model with best performance
yiliu30 Dec 6, 2022
9013738
modify IO document (#181)
WenjiaoYue Nov 28, 2022
6a172df
remove useless file in doc source (#182)
chensuyue Nov 28, 2022
dd4d4d9
Fixed benchmark error for tensorflow model (#177)
PenghuiCheng Nov 29, 2022
cc66832
Add export() PyTorch backend implementation for new API (#180)
xin3he Nov 29, 2022
9b1300b
Corrected pruning.md links, updated per channel examples. (#175)
YIYANGCAI Nov 29, 2022
1679a05
Adjust the hyperopt and sigopt as extras requirements (#173)
yiliu30 Nov 29, 2022
76676e2
IO docs bug fix (#188)
WenjiaoYue Nov 30, 2022
449e822
Neural Coder adding support of ONNX RT dynamic quant and static quant…
kaikaiyao Nov 30, 2022
42ed14c
update installation dependency (#185)
chensuyue Nov 30, 2022
ecd00c5
Set default value for use_bf16 and fixed random seed setting error (#…
PenghuiCheng Dec 1, 2022
64fa8aa
Turn off ITEX optimization pass (#196)
lvliang-intel Dec 2, 2022
ad6978a
Fixed UT error for bf16 op list for QAT mode (#200)
PenghuiCheng Dec 2, 2022
0ffdc5e
Disable multi instance for ITEX GPU benchmark (#204)
lvliang-intel Dec 2, 2022
32e7615
Revert "remove op-wise cfgs for testing. (#1521)" (#202)
intel-zhangyi Dec 2, 2022
cc45329
add examples for GPTJ (#162)
changwangss Dec 2, 2022
4a87b5b
Neural Coder mod launcher arg: "strategy" to "approach" (#201)
kaikaiyao Dec 3, 2022
bf0a33f
update publication_list.md (#212)
chensuyue Dec 5, 2022
518cd15
Added distributed training support for distillation of CNN-2. (#208)
XinyuYe-Intel Dec 5, 2022
3c482f8
Added distributed training support for distillation of MobileNetV2. …
XinyuYe-Intel Dec 5, 2022
d7213db
fix load issue (#194)
changwangss Dec 5, 2022
e283b27
Fix NTM-One-Shot failed with KeyError (#210)
lvliang-intel Dec 5, 2022
d1d375f
Fix TextRNN and centernet_hg104 tuning issue (#171)
lvliang-intel Dec 5, 2022
2e6e32c
add strategy kwargs for new api
yiliu30 Dec 6, 2022
8b41f0c
add uts
yiliu30 Dec 6, 2022
ddc188c
remove the line for debug
yiliu30 Dec 6, 2022
d6c8fc6
fixed some uts
yiliu30 Dec 6, 2022
2e189d8
add optimization_level in BaseQuantizationConfig
yiliu30 Dec 6, 2022
e1cfe60
add optimization_level to conf and pythonic_conf
yiliu30 Dec 6, 2022
aa37294
add UTs based on new API
yiliu30 Dec 7, 2022
ab0ce74
remove the UTs based on old API(yaml)
yiliu30 Dec 7, 2022
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 15 additions & 2 deletions .azure-pipelines/code-scan.yml
Original file line number Diff line number Diff line change
Expand Up @@ -9,13 +9,26 @@ pr:
paths:
include:
- neural_compressor
- setup.py

pool: ICX-16C

variables:
CODE_SCAN_LOG_PATH: ".azure-pipelines/scripts/codeScan/scanLog"

stages:
- stage: DocStyleCodeScan
displayName: DocStyle Code Scan
dependsOn: []
jobs:
- job: DocStyle
displayName: DocStyle
steps:
- template: template/code-scan-template.yml
parameters:
codeScanFileName: "pydocstyle"
uploadPath: "pydocstyle.log"

- stage: BanditCodeScan
displayName: Bandit Code Scan
dependsOn: []
Expand All @@ -26,7 +39,7 @@ stages:
- template: template/code-scan-template.yml
parameters:
codeScanFileName: "bandit"
uploadPath: "lpot-bandit.log"
uploadPath: "bandit.log"

- stage: PylintCodeScan
displayName: Pylint Code Scan
Expand All @@ -38,7 +51,7 @@ stages:
- template: template/code-scan-template.yml
parameters:
codeScanFileName: "pylint"
uploadPath: "lpot-pylint.json"
uploadPath: "pylint.json"

- stage: CopyRight
displayName: CopyRight Code Scan
Expand Down
3 changes: 2 additions & 1 deletion .azure-pipelines/docker/DockerfileCodeScan.devel
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@ RUN python -m pip install --no-cache-dir pylint==2.12.1\
tf_slim\
transformers\
horovod\
flask==2.1.3
flask==2.1.3 \
pydocstyle

WORKDIR /
1 change: 1 addition & 0 deletions .azure-pipelines/model-test.yml
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ pr:
paths:
include:
- neural_compressor
- setup.py
exclude:
- neural_compressor/ux

Expand Down
16 changes: 10 additions & 6 deletions .azure-pipelines/scripts/codeScan/bandit/bandit.sh
Original file line number Diff line number Diff line change
@@ -1,17 +1,21 @@
#!/bin/bash

source /neural-compressor/.azure-pipelines/scripts/change_color.sh
mkdir -p /neural-compressor/.azure-pipelines/scripts/codeScan/scanLog
bandit_log_dir="/neural-compressor/.azure-pipelines/scripts/codeScan/scanLog"
RESET="echo -en \\E[0m \\n" # close color

python -m bandit -r -lll -iii /neural-compressor/neural_compressor > $bandit_log_dir/lpot-bandit.log
log_dir="/neural-compressor/.azure-pipelines/scripts/codeScan/scanLog"
mkdir -p $log_dir

python -m bandit -r -lll -iii /neural-compressor/neural_compressor > $log_dir/bandit.log
exit_code=$?

# code-scan close
RESET="echo -en \\E[0m \\n"

$BOLD_YELLOW && echo " ----------------- Current bandit cmd start --------------------------" && $RESET
echo "python -m bandit -r -lll -iii /neural-compressor/neural_compressor > $log_dir/bandit.log"
$BOLD_YELLOW && echo " ----------------- Current bandit cmd end --------------------------" && $RESET

$BOLD_YELLOW && echo " ----------------- Current log file output start --------------------------"
cat $bandit_log_dir/lpot-bandit.log
cat $log_dir/bandit.log
$BOLD_YELLOW && echo " ----------------- Current log file output end --------------------------" && $RESET


Expand Down
25 changes: 25 additions & 0 deletions .azure-pipelines/scripts/codeScan/pydocstyle/pydocstyle.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
#!/bin/bash

source /neural-compressor/.azure-pipelines/scripts/change_color.sh
RESET="echo -en \\E[0m \\n" # close color

log_dir="/neural-compressor/.azure-pipelines/scripts/codeScan/scanLog"
mkdir -p $log_dir

pydocstyle --convention=google /neural-compressor/neural_compressor/experimental > $log_dir/pydocstyle.log
exit_code=$?


$BOLD_YELLOW && echo " ----------------- Current pydocstyle cmd start --------------------------" && $RESET
echo "python pydocstyle --convention=google /neural-compressor/neural_compressor/experimental > $log_dir/pydocstyle.log"
$BOLD_YELLOW && echo " ----------------- Current pydocstyle cmd end --------------------------" && $RESET

$BOLD_YELLOW && echo " ----------------- Current log file output start --------------------------"
cat $log_dir/pydocstyle.log
$BOLD_YELLOW && echo " ----------------- Current log file output end --------------------------" && $RESET


if [ ${exit_code} -ne 0 ] ; then
$BOLD_RED && echo "Error!! Please Click on the artifact button to download and view DocStyle error details." && $RESET; exit 1
fi
$BOLD_PURPLE && echo "Congratulations, DocStyle check passed!" && $LIGHT_PURPLE && echo " You can click on the artifact button to see the log details." && $RESET; exit 0
18 changes: 10 additions & 8 deletions .azure-pipelines/scripts/codeScan/pylint/pylint.sh
Original file line number Diff line number Diff line change
@@ -1,24 +1,26 @@
#!/bin/bash

source /neural-compressor/.azure-pipelines/scripts/change_color.sh
mkdir -p /neural-compressor/.azure-pipelines/scripts/codeScan/scanLog
pylint_log_dir="/neural-compressor/.azure-pipelines/scripts/codeScan/scanLog"
RESET="echo -en \\E[0m \\n" # close color

log_dir="/neural-compressor/.azure-pipelines/scripts/codeScan/scanLog"
mkdir -p $log_dir

pip install -r /neural-compressor/requirements.txt
pip install torch==1.12.0

python -m pylint -f json --disable=R,C,W,E1129 --enable=line-too-long --max-line-length=120 --extension-pkg-whitelist=numpy --ignored-classes=TensorProto,NodeProto --ignored-modules=tensorflow,torch,torch.quantization,torch.tensor,torchvision,mxnet,onnx,onnxruntime,intel_extension_for_pytorch /neural-compressor/neural_compressor > $pylint_log_dir/lpot-pylint.json
exit_code=$?
python -m pylint -f json --disable=R,C,W,E1129 --enable=line-too-long --max-line-length=120 --extension-pkg-whitelist=numpy --ignored-classes=TensorProto,NodeProto \
--ignored-modules=tensorflow,torch,torch.quantization,torch.tensor,torchvision,mxnet,onnx,onnxruntime,intel_extension_for_pytorch /neural-compressor/neural_compressor \
> $log_dir/pylint.json

# code-scan close
RESET="echo -en \\E[0m \\n"
exit_code=$?

$BOLD_YELLOW && echo " ----------------- Current pylint cmd start --------------------------" && $RESET
echo "python -m pylint -f json --disable=R,C,W,E1129 --enable=line-too-long --max-line-length=120 --extension-pkg-whitelist=numpy --ignored-classes=TensorProto,NodeProto --ignored-modules=tensorflow,torch,torch.quantization,torch.tensor,torchvision,mxnet,onnx,onnxruntime,intel_extension_for_pytorch /neural-compressor/neural_compressor > $pylint_log_dir/lpot-pylint.json"
echo "python -m pylint -f json --disable=R,C,W,E1129 --enable=line-too-long --max-line-length=120 --extension-pkg-whitelist=numpy --ignored-classes=TensorProto,NodeProto --ignored-modules=tensorflow,torch,torch.quantization,torch.tensor,torchvision,mxnet,onnx,onnxruntime,intel_extension_for_pytorch /neural-compressor/neural_compressor > $log_dir/pylint.json"
$BOLD_YELLOW && echo " ----------------- Current pylint cmd end --------------------------" && $RESET

$BOLD_YELLOW && echo " ----------------- Current log file output start --------------------------" && $RESET
cat $pylint_log_dir/lpot-pylint.json
cat $log_dir/pylint.json
$BOLD_YELLOW && echo " ----------------- Current log file output end --------------------------" && $RESET


Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -696,6 +696,7 @@ Goyal
gpg
GPG
gpt
GPTJ
gpu
gpus
GPUs
Expand Down Expand Up @@ -2378,3 +2379,9 @@ constfold
grappler
amsgrad
qoperator
apis
CPz
Nsh
UmK
fe
vmware
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,10 @@ matrix:
d: en_US.ISO8859-15
dictionary:
wordlists:
- ${DICT_DIR}/lpot_dict.txt
output: ${DICT_DIR}/lpot_dict.dic
- ${DICT_DIR}/inc_dict.txt
output: ${DICT_DIR}/inc_dict.dic
sources:
- ${REPO_DIR}/docs/*
- ${REPO_DIR}/docs/source/*.md
- ${REPO_DIR}/*.md
- ${REPO_DIR}/examples/**/*.md|!${REPO_DIR}/examples/pytorch/**/huggingface_models/**/*.md
- ${REPO_DIR}/neural_compressor/**/*.md
Expand Down
1 change: 1 addition & 0 deletions .azure-pipelines/scripts/models/generate_report.sh
Original file line number Diff line number Diff line change
Expand Up @@ -237,6 +237,7 @@ function generate_html_core {
status_png = "background-color:#90EE90";
} else {
status_png = "background-color:#FFD2D2";
job_status = "fail"
}
printf("<td style=\"%s\" colspan=2>%.2f</td>", status_png, target);
}
Expand Down
2 changes: 1 addition & 1 deletion .azure-pipelines/scripts/ut/env_setup.sh
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ echo "mxnet version is $mxnet_version"
if [[ "${tensorflow_version}" == *"-official" ]]; then
pip install tensorflow==${tensorflow_version%-official}
elif [[ "${tensorflow_version}" == "spr-base" ]]; then
pip install /tf_dataset/tf_binary/tensorflow*.whl
pip install /tf_dataset/tf_binary/221125/tensorflow*.whl
if [[ $? -ne 0 ]]; then
exit 1
fi
Expand Down
4 changes: 2 additions & 2 deletions .azure-pipelines/template/model-template.yml
Original file line number Diff line number Diff line change
Expand Up @@ -46,13 +46,13 @@ steps:
- script: |
docker exec ${{ parameters.modelContainerName }} bash -c "cd /neural-compressor/.azure-pipelines/scripts/models \
&& bash run_${{ parameters.framework }}_models_trigger.sh --model=${{ parameters.modelName }} --mode='int8_benchmark' --USE_TUNE_ACC=$(USE_TUNE_ACC) --PERF_STABLE_CHECK=$(PERF_STABLE_CHECK)"
continueOnError: true
condition: succeededOrFailed()
displayName: INT8 Benchmark

- script: |
docker exec ${{ parameters.modelContainerName }} bash -c "cd /neural-compressor/.azure-pipelines/scripts/models \
&& bash run_${{ parameters.framework }}_models_trigger.sh --model=${{ parameters.modelName }} --mode='fp32_benchmark' --USE_TUNE_ACC=$(USE_TUNE_ACC) --PERF_STABLE_CHECK=$(PERF_STABLE_CHECK)"
continueOnError: true
condition: succeededOrFailed()
displayName: FP32 Benchmark

- task: Bash@3
Expand Down
1 change: 1 addition & 0 deletions .azure-pipelines/ut-basic.yml
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@ pr:
include:
- neural_compressor
- test
- setup.py
exclude:
- neural_compressor/ux
- test/ux
Expand Down
1 change: 1 addition & 0 deletions .azure-pipelines/ut-ncoder.yml
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@ pr:
include:
- neural_coder
- test/neural_coder
- setup.py

pool: ICX-16C

Expand Down
1 change: 1 addition & 0 deletions .azure-pipelines/ut-ux.yml
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@ pr:
include:
- neural_compressor/ux
- test/ux
- setup.py

pool: ICX-16C

Expand Down
7 changes: 4 additions & 3 deletions .github/workflows/publish.yml
Original file line number Diff line number Diff line change
Expand Up @@ -14,16 +14,17 @@ jobs:
- uses: actions/checkout@v1
- name: Install dependencies
run: |
export PATH="$HOME/.local/bin:$PATH"
export PATH="$HOME/.local/bin:$PATH/docs"
sudo apt-get install -y python3-setuptools
pip3 install --user -r sphinx-requirements.txt
pip3 install --user -r docs/sphinx-requirements.txt
- name: Build the docs
run: |
export PATH="$HOME/.local/bin:$PATH"
cd docs/
make html
- name: Push the docs
uses: peaceiris/actions-gh-pages@v3
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
publish_dir: _build/html
publish_dir: docs/_build/html
publish_branch: latestHTML
34 changes: 0 additions & 34 deletions Makefile

This file was deleted.

Loading