PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
Update compatibility test and version to 0.10.2 (#1463)
Sun, Xuehao23c16c6c8a68
diff --git a/.azure-pipelines/compatibility-test.yml b/.azure-pipelines/compatibility-test.ymlindex c294e72af..754e47198 100644--- a/.azure-pipelines/compatibility-test.yml+++ b/.azure-pipelines/compatibility-test.yml@@ -69,17 +69,19 @@ stages:versionSpec: '$(python_version)'displayName: 'Use Python $(python_version)'- - script: |+ - bash: |python -m pip install --upgrade pip uvuv pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cpu- uv pip install .- pip list+ python setup.py sdist bdist_wheel+ uv pip install dist/*.tar.gz && uv pip uninstall auto-round+ uv pip install dist/*.whl+ uv pip listenv:PYTHONUNBUFFERED: '1'UV_NO_PROGRESS: '1'UV_SYSTEM_PYTHON: '1'displayName: 'Install dependencies'- - script: |- python -c "import auto_round"+ - bash: |+ python -c "import auto_round; print(auto_round.__version__)"displayName: 'Run compatibility test'diff --git a/.azure-pipelines/scripts/ut/run_ut_xpu.sh b/.azure-pipelines/scripts/ut/run_ut_xpu.shindex 61de032e8..c7e5da245 100644--- a/.azure-pipelines/scripts/ut/run_ut_xpu.sh+++ b/.azure-pipelines/scripts/ut/run_ut_xpu.sh@@ -10,6 +10,7 @@ git config --global --add safe.directory /auto-roundrm -rf /auto-round/auto_roundcd /auto-round/test || exit 1+export TQDM_MININTERVAL=60export ZE_AFFINITY_MASK=2,3 # set xpu affinityexport LD_LIBRARY_PATH=${HOME}/.venv/lib/:$LD_LIBRARY_PATHexport COVERAGE_RCFILE=/auto-round/.azure-pipelines/scripts/ut/.coveragediff --git a/.github/workflows/compatibility-test.yml b/.github/workflows/compatibility-test.ymlindex b558514b1..218368d4b 100644--- a/.github/workflows/compatibility-test.yml+++ b/.github/workflows/compatibility-test.yml@@ -60,8 +60,10 @@ jobs:python -m pip install --upgrade pip uv setuptoolsuv pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cpuuv pip install datasets --upgrade- uv pip install .- pip list+ python setup.py sdist bdist_wheel+ uv pip install dist/*.tar.gz && uv pip uninstall auto-round+ uv pip install dist/*.whl+ uv pip listenv:PYTHONUNBUFFERED: "1"UV_NO_PROGRESS: "1"@@ -71,7 +73,7 @@ jobs:- name: Run compatibility testrun: |set -xe- python -c "import auto_round"+ python -c "import auto_round; print(auto_round.__version__)"echo "============================================================================"auto-round --model_name Qwen/Qwen3-0.6B --bits 4 --iters 0 --nsamples 8echo "============================================================================"diff --git a/README.md b/README.mdindex 0aa1b20c7..62800bf4c 100644--- a/README.md+++ b/README.md@@ -10,7 +10,7 @@<h3> Advanced Quantization Algorithm for LLMs</h3>[](https://github.com/intel/auto-round)-[](https://github.com/intel/auto-round)+[](https://github.com/intel/auto-round)[](https://github.com/intel/auto-round/blob/main/LICENSE)<a href="https://huggingface.co/Intel"><img alt="Model Checkpoints" src="https://img.shields.io/badge/%F0%9F%A4%97%20HF-Models-F57C00">diff --git a/README_CN.md b/README_CN.mdindex 4ecfd5eb8..1228f24e8 100644--- a/README_CN.md+++ b/README_CN.md@@ -10,7 +10,7 @@<h3> 面向 LLM 的先进量化算法</h3>[](https://github.com/intel/auto-round)-[](https://github.com/intel/auto-round)+[](https://github.com/intel/auto-round)[](https://github.com/intel/auto-round/blob/main/LICENSE)<a href="https://huggingface.co/Intel"><img alt="Model Checkpoints" src="https://img.shields.io/badge/%F0%9F%A4%97%20HF-Models-F57C00">