Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Support true sequential options in gptq #1656

Merged
merged 22 commits into from May 23, 2024
Merged

Support true sequential options in gptq #1656

merged 22 commits into from May 23, 2024
+260 −102

Conversation

YIYANGCAI
Copy link
Collaborator

Type of Change

Feature

@YIYANGCAI
init commit
ab605aa 
Signed-off-by: YIYANGCAI <yiyang.cai@intel.com>
@YIYANGCAI YIYANGCAI added the WIP label Mar 8, 2024
@github-actions GitHub Actions
Copy link

github-actions bot commented Mar 8, 2024 •
edited

⚡ Required checks status: All passing 🟢

Groups summary

🟢 Code Scan Tests workflow
Check ID Status Error details
Code-Scan success ✅
Code-Scan (Bandit Code Scan Bandit) success ✅
Code-Scan (DocStyle Code Scan DocStyle) success ✅
Code-Scan (Pylint Code Scan Pylint) success ✅

These checks are required after the changes to neural_compressor/adaptor/pytorch.py, neural_compressor/adaptor/torch_utils/gptq.py.

🟢 Model Tests workflow
Check ID Status Error details
Model-Test success ✅
Model-Test (Generate Report GenerateReport) success ✅
Model-Test (Run ONNX Model resnet50-v1-12) success ✅
Model-Test (Run PyTorch Model resnet18) success ✅
Model-Test (Run PyTorch Model resnet18_fx) success ✅
Model-Test (Run TensorFlow Model darknet19) success ✅
Model-Test (Run TensorFlow Model inception_v1) success ✅
Model-Test (Run TensorFlow Model resnet-101) success ✅
Model-Test (Run TensorFlow Model resnet50v1.5) success ✅
Model-Test (Run TensorFlow Model ssd_mobilenet_v1_ckpt) success ✅
Model-Test (Run TensorFlow Model ssd_resnet50_v1) success ✅

These checks are required after the changes to neural_compressor/adaptor/pytorch.py, neural_compressor/adaptor/torch_utils/gptq.py.

🟢 Unit Tests basic workflow
Check ID Status Error details
UT-Basic success ✅
UT-Basic (Coverage Compare CollectDatafiles) success ✅
UT-Basic (Unit Test FWKs adaptor Test FWKs adaptor) success ✅
UT-Basic (Unit Test FWKs adaptor baseline Test FWKs adaptor baseline) success ✅
UT-Basic (Unit Test ITEX Test ITEX) success ✅
UT-Basic (Unit Test ITEX baseline Test ITEX baseline) success ✅
UT-Basic (Unit Test Pruning Test PyTorch Pruning) success ✅
UT-Basic (Unit Test Pruning Test TensorFlow Pruning) success ✅
UT-Basic (Unit Test Pruning baseline Test PyTorch Pruning baseline) success ✅
UT-Basic (Unit Test Pruning baseline Test TensorFlow Pruning baseline) success ✅
UT-Basic (Unit Test TF newAPI Test TF newAPI) success ✅
UT-Basic (Unit Test TF newAPI baseline Test TF newAPI baseline) success ✅
UT-Basic (Unit Test User facing API Test User facing API) success ✅
UT-Basic (Unit Test User facing API baseline Test User facing API baseline) success ✅
UT-Basic (Unit Test other basic case Test other basic case) success ✅
UT-Basic (Unit Test other cases baseline Test other cases baseline) success ✅
UT-Basic coverage report
Base coverage PR coverage Diff
Lines 86.949% 86.981% 0.032%
Branches 76.503% 76.554% 0.051%

These checks are required after the changes to neural_compressor/adaptor/pytorch.py, neural_compressor/adaptor/torch_utils/gptq.py, test/adaptor/pytorch_adaptor/test_weight_only_adaptor_pytorch.py, test/quantization/test_weight_only_quantization.py.

🟢 Unit Tests basic no coverage workflow
Check ID Status Error details
UT-Basic-No-Coverage success ✅
UT-Basic-No-Coverage (Unit Test FWKs adaptor Test FWKs adaptor) success ✅
UT-Basic-No-Coverage (Unit Test Pruning Test PyTorch Pruning) success ✅
UT-Basic-No-Coverage (Unit Test Pruning Test TensorFlow Pruning) success ✅
UT-Basic-No-Coverage (Unit Test User facing API Test User facing API) success ✅
UT-Basic-No-Coverage (Unit Test other basic case Test other basic case) success ✅

These checks are required after the changes to neural_compressor/adaptor/pytorch.py, neural_compressor/adaptor/torch_utils/gptq.py, test/adaptor/pytorch_adaptor/test_weight_only_adaptor_pytorch.py, test/quantization/test_weight_only_quantization.py.

🟢 Unit Tests ITREX workflow
Check ID Status Error details
UT-ITREX success ✅

These checks are required after the changes to neural_compressor/adaptor/pytorch.py, neural_compressor/adaptor/torch_utils/gptq.py.

Thank you for your contribution! 💜

Note
This comment is automatically generated and will be updates every 180 seconds within the next 6 hours. If you have any other questions, contact chensuyue or XuehaoSun for help.

YIYANGCAI and others added 5 commits March 27, 2024 23:15
@YIYANGCAI
Merge branch 'master' into gptq-true-sequential
9a875bc
@YIYANGCAI
fix some bugs
6f22c12 
Signed-off-by: YIYANGCAI <yiyang.cai@intel.com>
@pre-commit-ci
[pre-commit.ci] auto fixes from pre-commit.com hooks
5cec162 
for more information, see https://pre-commit.ci
@YIYANGCAI
fix typos
06e01c0 
Signed-off-by: YIYANGCAI <yiyang.cai@intel.com>
@YIYANGCAI
support passing parameters
00062ee 
Signed-off-by: YIYANGCAI <yiyang.cai@intel.com>
@YIYANGCAI YIYANGCAI removed the WIP label Mar 28, 2024
@chensuyue
Copy link
Contributor

@YIYANGCAI do we still need this PR?

@wenhuach21 wenhuach21 self-requested a review May 7, 2024 08:29
@YIYANGCAI
add lm_head quantization
bb28c6e 
Signed-off-by: YIYANGCAI <yiyang.cai@intel.com>
xin3he
xin3he approved these changes May 13, 2024
View reviewed changes
Copy link
Collaborator

@xin3he xin3he left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, I will raise another PR to support 3x.

...ples/pytorch/nlp/huggingface_models/language-modeling/quantization/llm/run_clm_no_trainer.py Outdated Show resolved Hide resolved
YIYANGCAI and others added 12 commits May 13, 2024 10:39
@YIYANGCAI
update documentations for true_sequential as well as lm_head.
3a050b3 
Signed-off-by: YIYANGCAI <yiyang.cai@intel.com>
@YIYANGCAI
Merge branch 'master' into gptq-true-sequential
dccdee6
@pre-commit-ci
[pre-commit.ci] auto fixes from pre-commit.com hooks
904cb6e 
for more information, see https://pre-commit.ci
@YIYANGCAI
remove redundant comments.
f47d9be 
Signed-off-by: YIYANGCAI <yiyang.cai@intel.com>
@YIYANGCAI
update uts
55125ff 
Signed-off-by: YIYANGCAI <yiyang.cai@intel.com>
@pre-commit-ci
[pre-commit.ci] auto fixes from pre-commit.com hooks
b3f5af5 
for more information, see https://pre-commit.ci
@YIYANGCAI
fix ut bugs
cfbabb3 
Signed-off-by: YIYANGCAI <yiyang.cai@intel.com>
@pre-commit-ci
[pre-commit.ci] auto fixes from pre-commit.com hooks
a9f6268 
for more information, see https://pre-commit.ci
@YIYANGCAI
fix pr ci bug
6dbde59 
Signed-off-by: YIYANGCAI <yiyang.cai@intel.com>
@YIYANGCAI
Merge branch 'master' into gptq-true-sequential
ff0f0f2
@YIYANGCAI
update true_sequential logic
ef04ea5 
Signed-off-by: YIYANGCAI <yiyang.cai@intel.com>
@YIYANGCAI
update true_sequential logic
73484cd 
Signed-off-by: YIYANGCAI <yiyang.cai@intel.com>
@changwangss changwangss mentioned this pull request May 21, 2024
Merged
@changwangss
Copy link
Collaborator

changwangss commented May 21, 2024 •
edited

ITREX PR intel/intel-extension-for-transformers#1559 apply the feature, @YIYANGCAI Could you help me double check if it has been applied ?

@YIYANGCAI
remove some codes
e2b5dad 
Signed-off-by: YIYANGCAI <yiyang.cai@intel.com>
@YIYANGCAI
restore codes.
5833fa3 
Signed-off-by: YIYANGCAI <yiyang.cai@intel.com>
@chensuyue chensuyue merged commit 92c9423 into master May 23, 2024
53 checks passed
@chensuyue chensuyue deleted the gptq-true-sequential branch May 23, 2024 06:03
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@chensuyue chensuyue chensuyue left review comments

@changwangss changwangss changwangss approved these changes

@xin3he xin3he xin3he approved these changes

@wenhuach21 wenhuach21 Awaiting requested review from wenhuach21

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
4 participants
@YIYANGCAI @chensuyue @changwangss @xin3he