Skip to content

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度

Add cpu & xpu nightly test (#2149)

Sun, Xuehao436dc247ad30
diff --git a/.azure-pipelines/nightly-test-cpu.yml b/.azure-pipelines/nightly-test-cpu.yml
new file mode 100644
index 000000000..e20ecc9c0
--- /dev/null
+++ b/.azure-pipelines/nightly-test-cpu.yml
@@ -0,0 +1,121 @@
+# Nightly pipeline: runs the slower CPU integration + e2e suites that are
+# excluded from the fast PR unit-test pipeline. Scheduled daily; can also be
+# triggered manually from the Azure DevOps UI.
+
+trigger: none
+pr:
+ autoCancel: true
+ drafts: false
+ branches:
+ include:
+ - main
+ paths:
+ include:
+ - test/integration/test_cpu
+ - .azure-pipelines/nightly-test-cpu.yml
+ - .azure-pipelines/scripts/ut/detect_changed_tests.sh
+
+parameters:
+ - name: unitTestParts
+ type: object
+ default:
+ - 1
+ - 2
+ - 3
+ - 4
+ - 5
+ - inc
+ - llmc
+
+schedules:
+ - cron: "0 18 * * *" # 02:00 Asia/Shanghai every day
+ displayName: Daily nightly run
+ branches:
+ include:
+ - main
+ always: true
+
+pool: INTEL-CPU
+
+variables:
+ IMAGE_NAME: "auto-round"
+ IMAGE_TAG: "py312"
+ UPLOAD_PATH: $(Build.SourcesDirectory)/log_dir
+ DOWNLOAD_PATH: $(Build.SourcesDirectory)/log_dir
+ ARTIFACT_NAME: "Nightly_coverage_report"
+ REPO: $(Build.Repository.Uri)
+
+stages:
+ - template: template/lib-build-template.yml
+ parameters:
+ enableChangeDetection: true
+
+ - stage: Unit_test
+ displayName: Unit Test
+ dependsOn: [DetectArkChanges, BuildArkWheel]
+ condition: and(succeeded('DetectArkChanges'), in(dependencies.BuildArkWheel.result, 'Succeeded', 'Skipped'))
+ variables:
+ BUILD_ARK_WHEEL: $[ stageDependencies.DetectArkChanges.Detect.outputs['SetArkWheelFlag.BUILD_ARK_WHEEL'] ]
+ jobs:
+ - job:
+ timeoutInMinutes: 60
+ strategy:
+ matrix:
+ ${{ each part in parameters.unitTestParts }}:
+ part_${{ part }}:
+ PART: ${{ part }}
+ steps:
+ - template: template/ut-template.yml
+ parameters:
+ dockerConfigName: "commonDockerConfig"
+ utScriptFileName: "run_ut"
+ uploadPath: $(UPLOAD_PATH)
+ utArtifact: "ut-$(PART)"
+ utTestMode: $(PART)
+ utContainerName: "AutoRoundUnitTest$(NODE_LABEL)"
+ buildARKWheel: $(BUILD_ARK_WHEEL)
+ filterChangedTests: true
+
+ - stage: Coverage
+ displayName: "Collect Coverage"
+ pool:
+ vmImage: "ubuntu-latest"
+ dependsOn: [Unit_test]
+ jobs:
+ - job: CollectDatafiles
+ steps:
+ - task: DownloadPipelineArtifact@2
+ inputs:
+ artifact:
+ patterns: '*_coverage/.coverage.*'
+ path: $(DOWNLOAD_PATH)
+
+ - task: UsePythonVersion@0
+ inputs:
+ versionSpec: '3.12'
+ displayName: 'Use Python 3.12'
+
+ - script: |
+ cd ${BUILD_SOURCESDIRECTORY}
+ pip install -U pip setuptools uv
+ uv pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cpu
+ uv pip install .
+ pip list
+ cd ${BUILD_SOURCESDIRECTORY}/.azure-pipelines/scripts
+ bash ut/collect_log.sh
+ env:
+ PYTHONUNBUFFERED: '1'
+ UV_NO_PROGRESS: '1'
+ UV_SYSTEM_PYTHON: '1'
+ displayName: "Collect UT Coverage"
+
+ - task: PublishPipelineArtifact@1
+ condition: succeededOrFailed()
+ inputs:
+ targetPath: $(UPLOAD_PATH)/coverage_PR
+ artifact: $(ARTIFACT_NAME)
+ publishLocation: "pipeline"
+
+ - task: PublishCodeCoverageResults@2
+ inputs:
+ summaryFileLocation: $(Build.SourcesDirectory)/log_dir/coverage_PR/coverage.xml
diff --git a/.azure-pipelines/nightly-test-xpu.yml b/.azure-pipelines/nightly-test-xpu.yml
index fee2a8067..66896637d 100644
--- a/.azure-pipelines/nightly-test-xpu.yml
+++ b/.azure-pipelines/nightly-test-xpu.yml
@@ -3,7 +3,24 @@
# Scheduled daily; can also be triggered manually from the Azure DevOps UI.
trigger: none
-pr: none
+pr:
+ autoCancel: true
+ drafts: false
+ branches:
+ include:
+ - main
+ paths:
+ include:
+ - test/integration/test_xpu
+ - .azure-pipelines/nightly-test-xpu.yml
+ - .azure-pipelines/scripts/ut/detect_changed_tests.sh
+
+parameters:
+ - name: xpuTestParts
+ type: object
+ default:
+ - nightly
+ - llmc
schedules:
- cron: "0 19 * * *" # 03:00 Asia/Shanghai every day
@@ -28,7 +45,7 @@ variables:
stages:
- template: template/lib-build-template.yml
parameters:
- enableChangeDetection: false
+ enableChangeDetection: true
publishToTestPyPI: false
- stage: Nightly_xpu_test
@@ -39,19 +56,24 @@ stages:
- job:
displayName: Nightly XPU Test
timeoutInMinutes: 180
+ strategy:
+ matrix:
+ ${{ each part in parameters.xpuTestParts }}:
+ part_${{ part }}:
+ PART: ${{ part }}
steps:
- template: template/ut-template.yml
parameters:
dockerConfigName: "commonDockerConfig"
utScriptFileName: "run_ut_xpu"
- # "integration" enables the XPU LLMC integration suite in run_ut_xpu.sh
- utTestMode: "integration"
+ utTestMode: $(PART)
uploadPath: $(UPLOAD_PATH)
- utArtifact: "nightly-xpu"
+ utArtifact: "$(PART)-xpu"
imageTag: $(IMAGE_TAG)
dockerFileName: $(DOCKERFILE_NAME)
utContainerName: "AutoRoundNightlyXPU$(NODE_LABEL)"
buildARKWheel: "false"
+ filterChangedTests: true
- task: UseDotNet@2
displayName: 'Use .NET Core sdk 7.0.x'
@@ -59,6 +81,6 @@ stages:
version: 7.0.x
- task: PublishCodeCoverageResults@2
- condition: succeededOrFailed()
+ condition: and(succeededOrFailed(), ne(variables['HAS_COVERAGE'], 'false'))
inputs:
summaryFileLocation: $(UPLOAD_PATH)/coverage.xml
diff --git a/.azure-pipelines/nightly-test.yml b/.azure-pipelines/nightly-test.yml
deleted file mode 100644
index a4cbef256..000000000
--- a/.azure-pipelines/nightly-test.yml
+++ /dev/null
@@ -1,51 +0,0 @@
-# Nightly pipeline: runs the slower CPU integration + e2e suites that are
-# excluded from the fast PR unit-test pipeline. Scheduled daily; can also be
-# triggered manually from the Azure DevOps UI.
-
-trigger: none
-pr: none
-
-schedules:
- - cron: "0 18 * * *" # 02:00 Asia/Shanghai every day
- displayName: Daily nightly run
- branches:
- include:
- - main
- always: true
-
-pool: ICX-16C
-
-variables:
- IMAGE_NAME: "auto-round"
- IMAGE_TAG: "py312"
- UPLOAD_PATH: $(Build.SourcesDirectory)/log_dir
- DOWNLOAD_PATH: $(Build.SourcesDirectory)/log_dir
- ARTIFACT_NAME: "Nightly_coverage_report"
- REPO: $(Build.Repository.Uri)
-
-stages:
- - template: template/lib-build-template.yml
- parameters:
- enableChangeDetection: false
-
- - stage: Nightly_test
- displayName: Nightly Integration + E2E Test
- dependsOn: [BuildArkWheel]
- condition: in(dependencies.BuildArkWheel.result, 'Succeeded', 'Skipped')
- jobs:
- - job:
- timeoutInMinutes: 180
- steps:
- - template: template/ut-template.yml
- parameters:
- dockerConfigName: "commonDockerConfig"
- utScriptFileName: "run_nightly"
- uploadPath: $(UPLOAD_PATH)
- utArtifact: "nightly"
- utContainerName: "AutoRoundNightly$(NODE_LABEL)"
- buildARKWheel: "false"
-
- - task: PublishCodeCoverageResults@2
- condition: succeededOrFailed()
- inputs:
- summaryFileLocation: $(UPLOAD_PATH)/coverage.xml
diff --git a/.azure-pipelines/scripts/cuda_unit_test/run_cuda_ut.sh b/.azure-pipelines/scripts/cuda_unit_test/run_cuda_ut.sh
index 9125451a1..5c3579656 100644
--- a/.azure-pipelines/scripts/cuda_unit_test/run_cuda_ut.sh
+++ b/.azure-pipelines/scripts/cuda_unit_test/run_cuda_ut.sh
@@ -19,10 +19,17 @@ for i in "$@"; do
done
source ${BUILD_SOURCESDIRECTORY}/.azure-pipelines/scripts/change_color.sh
+# Change-based test selection helpers. REPO_DIR points the detector at the
+# agent checkout instead of the container default (/auto-round).
+REPO_DIR="${BUILD_SOURCESDIRECTORY}"
+source ${BUILD_SOURCESDIRECTORY}/.azure-pipelines/scripts/ut/detect_changed_tests.sh
LOG_DIR="${BUILD_SOURCESDIRECTORY}/log_dir"
mkdir -p "${LOG_DIR}"
SUMMARY_LOG="${LOG_DIR}/results_summary.log"
+# print_summary reads this file unconditionally; a matrix part that selects no
+# test never writes it, so make sure it always exists.
+touch "${SUMMARY_LOG}"
function setup_environment() {
export TZ='Asia/Shanghai'
@@ -82,6 +89,12 @@ function run_unit_test() {
fi
end_line=$(( start_line + chunk_size - 1 ))
selected_files=$(sed -n "${start_line},${end_line}p" all_tests.txt)
+ selected_files=$(filter_changed_tests "test" "${selected_files}")
+
+ if [ -z "${selected_files}" ]; then
+ echo "No changed CUDA unit test file in part ${test_part}, skip."
+ return 0
+ fi
for test_file in ${selected_files}; do
echo "##[group]Running ${test_file}..."
@@ -203,11 +216,15 @@ function run_unit_test_vllm() {
function main() {
setup_environment
+ init_changed_tests
if [ "${test_case}" == "nightly" ]; then
run_unit_test_sglang
run_unit_test_llmc
run_unit_test_vllm
elif [ "${test_case}" == "ci" ]; then
+ # Mirror the selection below: tests excluded from the ci run (vlms,
+ # llmc, sglang, vllm, multiple_card) must not enable filtering.
+ scope_changed_tests "$(cd "${BUILD_SOURCESDIRECTORY}" && find test/unit/test_cuda -type f -name "test_*.py" | grep -Ev "vlms|llmc|sglang|vllm|multiple_card")"
run_unit_test
else
echo "##[error]Invalid test case specified: ${test_case}. Please use 'nightly' or 'ci'."
diff --git a/.azure-pipelines/scripts/ut/collect_log.sh b/.azure-pipelines/scripts/ut/collect_log.sh
index d6a7828d5..5113492ab 100644
--- a/.azure-pipelines/scripts/ut/collect_log.sh
+++ b/.azure-pipelines/scripts/ut/collect_log.sh
@@ -7,6 +7,12 @@ cd "${BUILD_SOURCESDIRECTORY}/log_dir"
echo "collect coverage for PR branch"
mkdir -p coverage_PR
+# Every matrix part may legitimately select no test (change-based filtering),
+# in which case there is nothing to combine.
+if ! compgen -G "ut-*/.coverage.*" > /dev/null; then
+ echo "no coverage data found, skip coverage collection."
+ exit 0
+fi
cp ut-*/.coverage.* ./coverage_PR/
cd coverage_PR
coverage combine --keep --rcfile=${COVERAGE_RCFILE}
diff --git a/.azure-pipelines/scripts/ut/detect_changed_tests.sh b/.azure-pipelines/scripts/ut/detect_changed_tests.sh
new file mode 100644
index 000000000..f4124f635
--- /dev/null
+++ b/.azure-pipelines/scripts/ut/detect_changed_tests.sh
@@ -0,0 +1,167 @@
+#!/bin/bash
+# Detect the test files modified by the current change set.
+#
+# Usage:
+# source detect_changed_tests.sh
+# detect_changed_tests # prints repo-relative test files, one per line
+# returns 0 -> filtering applies (a change set was detected)
+# returns 1 -> filtering does NOT apply, caller should run the full suite
+#
+# Detection order:
+# 1. Filtering is opt-in: unless FILTER_CHANGED_TESTS is truthy the full suite
+# runs. This keeps pipelines that do not request it running everything.
+# 2. Only PR builds are filtered. When BUILD_REASON is set and is not
+# "PullRequest" (e.g. a scheduled or manual run) the full suite runs.
+# 3. Diff the working tree against BASE_REF (default origin/main, or the PR
+# target branch when available). Filtering only kicks in when the change
+# set is EXCLUSIVELY test files (test/**/test_*.py); if any other file
+# changed (source, helpers, conftest, deletions, ...) the full suite runs.
+#
+# Only existing files matching test/**/test_*.py are reported; a deleted test
+# file counts as a non-test change so the full suite runs.
+
+REPO_DIR="${REPO_DIR:-/auto-round}"
+# Prefer the PR target branch reported by Azure DevOps; fall back to origin/main.
+_pr_target="${SYSTEM_PULLREQUEST_TARGETBRANCH#refs/heads/}"
+BASE_REF="${BASE_REF:-origin/${_pr_target:-main}}"
+
+detect_changed_tests() {
+ # Filtering is opt-in; pipelines that do not request it run everything.
+ case "${FILTER_CHANGED_TESTS:-}" in
+ 1 | true | True | TRUE) ;;
+ *)
+ echo "FILTER_CHANGED_TESTS not enabled, run full suite." >&2
+ return 1
+ ;;
+ esac
+
+ # Only PR builds are filtered; scheduled/manual runs execute everything.
+ if [ -n "${BUILD_REASON:-}" ] && [ "${BUILD_REASON}" != "PullRequest" ]; then
+ echo "BUILD_REASON=${BUILD_REASON} is not a PR, run full suite." >&2
+ return 1
+ fi
+
+ if ! command -v git > /dev/null 2>&1; then
+ echo "git not available, run full suite." >&2
+ return 1
+ fi
+
+ cd "${REPO_DIR}" 2>/dev/null || return 1
+ git config --global --add safe.directory "${REPO_DIR}" > /dev/null 2>&1 || true
+
+ # Best-effort fetch so BASE_REF resolves; ignore failures (offline runners).
+ # CI checkouts are often shallow, which breaks merge-base; unshallow first.
+ local base_branch="${BASE_REF#origin/}"
+ if [ "$(git rev-parse --is-shallow-repository 2>/dev/null)" = "true" ]; then
+ git fetch --quiet --unshallow origin > /dev/null 2>&1 || true
+ fi
+ git fetch --quiet origin "+refs/heads/${base_branch}:refs/remotes/origin/${base_branch}" > /dev/null 2>&1 || true
+
+ local base_sha
+ base_sha="$(git merge-base "${BASE_REF}" HEAD 2>/dev/null)" || base_sha=""
+ if [ -z "${base_sha}" ]; then
+ echo "cannot resolve base ref '${BASE_REF}', run full suite." >&2
+ return 1
+ fi
+
+ local all_changed test_changed non_test
+ # NOTE: no --diff-filter here. Deletions must stay visible, otherwise a PR
+ # that removes a source file and touches a test would look test-only.
+ all_changed="$(git diff --name-only "${base_sha}" HEAD 2>/dev/null)"
+ if [ -z "${all_changed}" ]; then
+ echo "no changed file detected, run full suite." >&2
+ return 1
+ fi
+
+ # Added/copied/modified/renamed only: a deleted test cannot be executed.
+ test_changed="$(git diff --name-only --diff-filter=ACMR "${base_sha}" HEAD -- 'test/**/test_*.py' 2>/dev/null)"
+ if [ -z "${test_changed}" ]; then
+ echo "no changed test file detected, run full suite." >&2
+ return 1
+ fi
+
+ # Only filter when the change set is exclusively test files. Any other file
+ # (source, test helpers, conftest, requirements, ...) may affect many tests,
+ # so fall back to the full suite.
+ non_test="$(comm -23 <(printf '%s\n' "${all_changed}" | sort -u) \
+ <(printf '%s\n' "${test_changed}" | sort -u))"
+ if [ -n "${non_test}" ]; then
+ echo "non-test files changed, run full suite:" >&2
+ printf ' %s\n' ${non_test} >&2
+ return 1
+ fi
+
+ printf '%s\n' "${test_changed}"
+ return 0
+}
+
+# ---------------------------------------------------------------------------
+# Shared helpers for the run_ut*.sh scripts.
+# ---------------------------------------------------------------------------
+
+# Populated by init_changed_tests(): whitespace separated repo-relative test
+# files touched by this change set. FILTER_TESTS=1 means only run those files.
+CHANGED_TEST_FILES=""
+FILTER_TESTS=0
+
+# Resolve the change set once and cache it for filter_changed_tests().
+init_changed_tests() {
+ local changed
+ if changed=$(detect_changed_tests); then
+ CHANGED_TEST_FILES=$(printf '%s' "${changed}" | tr '\n' ' ')
+ FILTER_TESTS=1
+ echo "Only running changed test files: ${CHANGED_TEST_FILES}"
+ else
+ FILTER_TESTS=0
+ echo "Running the full test suite."
+ fi
+}
+
+# Disable filtering when none of the changed tests can be executed by this
+# runner. Without this every matrix part could end up with an empty selection
+# and the job would produce no results, no summary and no coverage at all.
+# $@: repo-relative paths of every test this runner is able to execute.
+scope_changed_tests() {
+ [ "${FILTER_TESTS}" = "1" ] || return 0
+
+ local scope="$*"
+ local changed candidate
+ for changed in ${CHANGED_TEST_FILES}; do
+ for candidate in ${scope}; do
+ if [ "${changed}" = "${candidate#./}" ]; then
+ return 0
+ fi
+ done
+ done
+
+ echo "Changed tests are outside this runner's scope, run the full test suite."
+ FILTER_TESTS=0
+}
+
+# Keep only the entries of a candidate list that were modified by this PR.
+# $1: repo-relative directory the candidates are relative to (e.g. "test")
+# $2: newline separated candidate test files (e.g. "./unit/test_cpu/test_a.py")
+filter_changed_tests() {
+ local base_dir=$1
+ local candidates=$2
+
+ if [ "${FILTER_TESTS}" != "1" ]; then
+ printf '%s' "${candidates}"
+ return 0
+ fi
+
+ local kept=""
+ local candidate normalized changed
+ while IFS= read -r candidate; do
+ [ -z "${candidate}" ] && continue
+ normalized="${base_dir}/${candidate#./}"
+ for changed in ${CHANGED_TEST_FILES}; do
+ if [ "${changed#./}" = "${normalized}" ]; then
+ kept+="${candidate}"$'\n'
+ break
+ fi
+ done
+ done <<< "${candidates}"
+
+ printf '%s' "${kept}"
+}
diff --git a/.azure-pipelines/scripts/ut/run_ut.sh b/.azure-pipelines/scripts/ut/run_ut.sh
index 14e4db8cf..b82151096 100644
--- a/.azure-pipelines/scripts/ut/run_ut.sh
+++ b/.azure-pipelines/scripts/ut/run_ut.sh
@@ -1,14 +1,18 @@
#!/bin/bash
set -e
-test_part=$1
+test_part=${UT_MODE}
source /auto-round/.azure-pipelines/scripts/change_color.sh
+source /auto-round/.azure-pipelines/scripts/ut/detect_changed_tests.sh
LOG_DIR=/auto-round/log_dir
mkdir -p "${LOG_DIR}"
SUMMARY_LOG="${LOG_DIR}/results_summary.log"
+TIMEOUT=30
+SESSION_TIMEOUT=600
+
function setup_environment() {
echo "##[group]set up UT env..."
echo "NUMA_NODE=${NUMA_NODE}"
@@ -72,6 +76,12 @@ function run_unit_test() {
fi
end_line=$(( start_line + chunk_size - 1 ))
selected_files=$(sed -n "${start_line},${end_line}p" all_tests.txt)
+ selected_files=$(filter_changed_tests "test" "${selected_files}")
+
+ if [ -z "${selected_files}" ]; then
+ echo "No changed unit test file in part ${test_part}, skip."
+ return 0
+ fi
for test_file in ${selected_files}; do
echo "##[group]Running ${test_file}..."
@@ -79,7 +89,7 @@ function run_unit_test() {
local ut_log_name=${LOG_DIR}/unittest_${test_basename}.log
numactl --physcpubind="${NUMA_CPUSET:-0-15}" --membind="${NUMA_NODE:-0}" \
- pytest -m "not skip_ci" --timeout=30 --session-timeout=600 \
+ pytest -m "not skip_ci" --timeout=${TIMEOUT} --session-timeout=${SESSION_TIMEOUT} \
--cov=auto_round --cov-report= --cov-append \
-vs --junitxml="${ut_log_name%.log}.xml" ${test_file} 2>&1 | tee ${ut_log_name}
echo "##[endgroup]"
@@ -87,26 +97,41 @@ function run_unit_test() {
}
function run_inc_unit_test() {
+ local selected_files
+ selected_files=$(filter_changed_tests "test/integration" \
+ "$(cd /auto-round/test/integration && find ./test_cpu -name "test_inc*.py" | sort)")
+ if [ -z "${selected_files}" ]; then
+ echo "No changed INC test file, skip."
+ return 0
+ fi
+
echo "##[group]set up INC UT env..."
INC_PT_ONLY=1 uv pip install -r /auto-round/test/integration/test_cpu/requirements_inc.txt --extra-index-url https://download.pytorch.org/whl/cpu
echo "##[endgroup]"
cd /auto-round/test/integration || exit 1
- for test_file in $(find ./test_cpu -name "test_inc*.py" | sort); do
+ for test_file in ${selected_files}; do
echo "##[group]Running ${test_file}..."
local test_basename=$(basename ${test_file} .py)
local ut_log_name=${LOG_DIR}/unittest_${test_basename}.log
numactl --physcpubind="${NUMA_CPUSET:-0-15}" --membind="${NUMA_NODE:-0}" \
- pytest --timeout=30 --session-timeout=600 \
- --cov=auto_round --cov-report= --cov-append \
+ pytest --cov=auto_round --cov-report= --cov-append \
-vs --junitxml="${ut_log_name%.log}.xml" ${test_file} 2>&1 | tee ${ut_log_name}
echo "##[endgroup]"
done
}
function run_llmc_unit_test() {
+ local selected_files
+ selected_files=$(filter_changed_tests "test/integration" \
+ "$(cd /auto-round/test/integration && find ./test_cpu -name "test_llmc*.py" | sort)")
+ if [ -z "${selected_files}" ]; then
+ echo "No changed LLMC test file, skip."
+ return 0
+ fi
+
echo "##[group]set up LLMC UT env..."
BUILD_TYPE="nightly" uv pip install -r /auto-round/test/integration/test_cpu/requirements_llmc.txt --extra-index-url https://download.pytorch.org/whl/cpu
uv pip uninstall auto-round
@@ -115,36 +140,42 @@ function run_llmc_unit_test() {
cd /auto-round/test/integration || exit 1
- for test_file in $(find ./test_cpu -name "test_llmc*.py" | sort); do
+ for test_file in ${selected_files}; do
echo "##[group]Running ${test_file}..."
local test_basename=$(basename ${test_file} .py)
local ut_log_name=${LOG_DIR}/unittest_${test_basename}.log
numactl --physcpubind="${NUMA_CPUSET:-0-15}" --membind="${NUMA_NODE:-0}" \
- pytest --timeout=30 --session-timeout=600 \
- --cov=auto_round --cov-report= --cov-append \
+ pytest --cov=auto_round --cov-report= --cov-append \
-vs --junitxml="${ut_log_name%.log}.xml" ${test_file} 2>&1 | tee ${ut_log_name}
echo "##[endgroup]"
done
}
function collect_log() {
+ touch "${SUMMARY_LOG}"
python /auto-round/.azure-pipelines/scripts/ut/collect_result.py \
--test-type "Unit Tests" --log-pattern "unittest_test_*.log" --log-dir ${LOG_DIR} --summary-log ${SUMMARY_LOG}
- cp .coverage "${LOG_DIR}/.coverage.part${test_part}"
+ if [ -f .coverage ]; then
+ cp .coverage "${LOG_DIR}/.coverage.part${test_part}"
+ fi
}
function main() {
setup_environment
- run_unit_test
- if [ "$test_part" -eq 5 ] && [ "$NIGHTLY_TEST" = 1 ]; then
+ init_changed_tests
+ scope_changed_tests "$(cd /auto-round && find test/unit/test_cpu test/integration/test_cpu -name "test_*.py" 2>/dev/null)"
+ if [ "$test_part" = "inc" ]; then
run_inc_unit_test
+ elif [ "$test_part" = "llmc" ]; then
run_llmc_unit_test
+ else
+ run_unit_test
fi
collect_log
check_storage_usage
print_summary
}
-main
+main "$@"
diff --git a/.azure-pipelines/scripts/ut/run_ut_hpu.sh b/.azure-pipelines/scripts/ut/run_ut_hpu.sh
index 77f88d346..7e821eb72 100644
--- a/.azure-pipelines/scripts/ut/run_ut_hpu.sh
+++ b/.azure-pipelines/scripts/ut/run_ut_hpu.sh
@@ -1,6 +1,7 @@
#!/bin/bash
set -e
source /auto-round/.azure-pipelines/scripts/change_color.sh
+source /auto-round/.azure-pipelines/scripts/ut/detect_changed_tests.sh
function setup_environment() {
# install requirements
@@ -28,7 +29,14 @@ function setup_environment() {
function run_unit_test() {
auto_round_path=$(python -c 'import auto_round; print(auto_round.__path__[0])')
- for test_file in $(find ./unit/test_hpu -name "test*.py" | sort); do
+ local hpu_tests
+ hpu_tests=$(filter_changed_tests "test" "$(find ./unit/test_hpu -name "test*.py" | sort)")
+ if [ -z "${hpu_tests}" ]; then
+ echo "No changed HPU test file, skip."
+ return 0
+ fi
+
+ for test_file in ${hpu_tests}; do
local test_basename=$(basename ${test_file} .py)
echo "##[group]Running ${test_file} in HPU lazy mode..."
@@ -55,21 +63,29 @@ function print_summary() {
}
function collect_log() {
+ touch "${SUMMARY_LOG}"
python /auto-round/.azure-pipelines/scripts/ut/collect_result.py \
--test-type "Unit Tests" --log-pattern "unittest_*.log" --log-dir ${LOG_DIR} --summary-log ${SUMMARY_LOG}
- cp .coverage "${LOG_DIR}/.coverage"
- python -m coverage xml -o "${LOG_DIR}/coverage.xml"
- python -m coverage html -d "${LOG_DIR}/htmlcov"
+ if [ -f .coverage ]; then
+ cp .coverage "${LOG_DIR}/.coverage"
+ python -m coverage xml -o "${LOG_DIR}/coverage.xml"
+ python -m coverage html -d "${LOG_DIR}/htmlcov"
+ else
+ echo "No coverage data (no test selected), skip coverage report."
+ echo "##vso[task.setvariable variable=HAS_COVERAGE]false"
+ fi
}
function print_coverage() {
echo "##[group]overall code coverage..."
- python -m coverage report
+ [ -f .coverage ] && python -m coverage report || echo "No coverage data."
echo "##[endgroup]"
}
function main() {
setup_environment
+ init_changed_tests
+ scope_changed_tests "$(cd /auto-round && find test/unit/test_hpu -name "test_*.py" 2>/dev/null)"
run_unit_test
collect_log
print_coverage
diff --git a/.azure-pipelines/scripts/ut/run_ut_xpu.sh b/.azure-pipelines/scripts/ut/run_ut_xpu.sh
index 642f1172f..edc06dfc3 100644
--- a/.azure-pipelines/scripts/ut/run_ut_xpu.sh
+++ b/.azure-pipelines/scripts/ut/run_ut_xpu.sh
@@ -2,6 +2,10 @@
set -e
source /auto-round/.azure-pipelines/scripts/change_color.sh
+source /auto-round/.azure-pipelines/scripts/ut/detect_changed_tests.sh
+
+TIMEOUT=30
+SESSION_TIMEOUT=600
function setup_environment() {
echo "##[group]set up UT env..."
@@ -33,25 +37,29 @@ function setup_environment() {
function run_unit_test() {
auto_round_path=$(python -c 'import auto_round; print(auto_round.__path__[0])')
- for test_file in $(find ./unit/test_ark -name "test*.py" | sort); do
+ local ark_tests xpu_tests
+ ark_tests=$(filter_changed_tests "test" "$(find ./unit/test_ark -name "test*.py" | sort)")
+ xpu_tests=$(filter_changed_tests "test" "$(find ./unit/test_xpu -name "test*.py" | sort)")
+
+ for test_file in ${ark_tests}; do
local test_basename=$(basename ${test_file} .py)
echo "##[group]Running ark ${test_file}..."
local ut_log_name="${LOG_DIR}/unittest_ark_${test_basename}.log"
numactl --physcpubind="${NUMA_CPUSET:-0-27}" --membind="${NUMA_NODE:-0}" \
- pytest --timeout=30 --session-timeout=600 \
+ pytest --timeout=${TIMEOUT} --session-timeout=${SESSION_TIMEOUT} \
--cov="${auto_round_path}" --cov-report= --cov-append -vs \
--junitxml="${ut_log_name%.log}.xml" ${test_file} 2>&1 | tee ${ut_log_name}
echo "##[endgroup]"
done
- for test_file in $(find ./unit/test_xpu -name "test*.py" | sort); do
+ for test_file in ${xpu_tests}; do
local test_basename=$(basename ${test_file} .py)
echo "##[group]Running xpu ${test_file}..."
local ut_log_name="${LOG_DIR}/unittest_xpu_${test_basename}.log"
numactl --physcpubind="${NUMA_CPUSET:-0-27}" --membind="${NUMA_NODE:-0}" \
- pytest --timeout=30 --session-timeout=600 \
+ pytest --timeout=${TIMEOUT} --session-timeout=${SESSION_TIMEOUT} \
--cov="${auto_round_path}" --cov-report= --cov-append -vs \
--junitxml="${ut_log_name%.log}.xml" ${test_file} 2>&1 | tee ${ut_log_name}
echo "##[endgroup]"
@@ -59,6 +67,13 @@ function run_unit_test() {
}
function run_unit_test_llmc() {
+ local llmc_tests
+ llmc_tests=$(filter_changed_tests "test" "$(find ./integration/test_xpu -name "test_llmc_integration.py" | sort)")
+ if [ -z "${llmc_tests}" ]; then
+ echo "No changed XPU LLMC test file, skip."
+ return 0
+ fi
+
echo "##[group]set up llmc UT env..."
BUILD_TYPE="nightly" uv pip install -r ./unit/test_xpu/requirements_llmc.txt
uv pip list
@@ -66,13 +81,13 @@ function run_unit_test_llmc() {
auto_round_path=$(python -c 'import auto_round; print(auto_round.__path__[0])')
- for test_file in $(find ./integration/test_xpu -name "test_llmc_integration.py" | sort); do
+ for test_file in ${llmc_tests}; do
local test_basename=$(basename ${test_file} .py)
echo "##[group]Running xpu llmc ${test_file}..."
local ut_log_name="${LOG_DIR}/unittest_xpu_${test_basename}.log"
numactl --physcpubind="${NUMA_CPUSET:-0-27}" --membind="${NUMA_NODE:-0}" \
- pytest --timeout=30 --session-timeout=600 \
+ pytest --timeout=${TIMEOUT} --session-timeout=${SESSION_TIMEOUT} \
--cov="${auto_round_path}" --cov-report= --cov-append -vs \
--junitxml="${ut_log_name%.log}.xml" ${test_file} 2>&1 | tee ${ut_log_name}
echo "##[endgroup]"
@@ -85,23 +100,34 @@ function print_summary() {
}
function collect_log() {
+ touch "${SUMMARY_LOG}"
python /auto-round/.azure-pipelines/scripts/ut/collect_result.py \
--test-type "Unit Tests" --log-pattern "unittest_*.log" --log-dir ${LOG_DIR} --summary-log ${SUMMARY_LOG}
- cp .coverage "${LOG_DIR}/.coverage"
- python -m coverage xml -o "${LOG_DIR}/coverage.xml"
- python -m coverage html -d "${LOG_DIR}/htmlcov"
+ if [ -f .coverage ]; then
+ cp .coverage "${LOG_DIR}/.coverage"
+ python -m coverage xml -o "${LOG_DIR}/coverage.xml"
+ python -m coverage html -d "${LOG_DIR}/htmlcov"
+ else
+ echo "No coverage data (no test selected), skip coverage report."
+ echo "##vso[task.setvariable variable=HAS_COVERAGE]false"
+ fi
}
function print_coverage() {
echo "##[group]overall code coverage..."
- python -m coverage report
+ [ -f .coverage ] && python -m coverage report || echo "No coverage data."
echo "##[endgroup]"
}
function main() {
setup_environment
- run_unit_test
- run_unit_test_llmc
+ init_changed_tests
+ scope_changed_tests "$(cd /auto-round && find test/unit/test_ark test/unit/test_xpu test/integration/test_xpu -name "test_*.py" 2>/dev/null)"
+ if [[ "${UT_MODE}" == "llmc" ]]; then
+ run_unit_test_llmc
+ else
+ run_unit_test
+ fi
collect_log
print_coverage
print_summary
diff --git a/.azure-pipelines/template/ut-template.yml b/.azure-pipelines/template/ut-template.yml
index 7a3a57794..0c87ce50b 100644
--- a/.azure-pipelines/template/ut-template.yml
+++ b/.azure-pipelines/template/ut-template.yml
@@ -32,6 +32,11 @@ parameters:
- name: buildARKWheel
type: string
default: "false"
+ # Opt-in: on PR builds only run the test files touched by the PR. Off by
+ # default so the fast PR unit-test pipeline keeps running the full suite.
+ - name: filterChangedTests
+ type: boolean
+ default: false
steps:
@@ -100,9 +105,15 @@ steps:
- script: |
set -eo pipefail
- docker exec -e NUMA_NODE=${NUMA_NODE} -e NUMA_CPUSET=${NUMA_CPUSET} -e ZE_AFFINITY_MASK=${ZE_AFFINITY_MASK} ${{ parameters.utContainerName }} \
- bash -c "cd /auto-round/.azure-pipelines/scripts \
- && bash ut/${{ parameters.utScriptFileName }}.sh ${{ parameters.utTestMode }}"
+ docker exec -e NUMA_NODE=${NUMA_NODE} \
+ -e NUMA_CPUSET=${NUMA_CPUSET} \
+ -e ZE_AFFINITY_MASK=${ZE_AFFINITY_MASK} \
+ -e UT_MODE=${{ parameters.utTestMode }} \
+ -e BUILD_REASON=${BUILD_REASON} \
+ -e SYSTEM_PULLREQUEST_TARGETBRANCH=${SYSTEM_PULLREQUEST_TARGETBRANCH} \
+ -e FILTER_CHANGED_TESTS=${{ lower(parameters.filterChangedTests) }} \
+ ${{ parameters.utContainerName }} \
+ bash -c "cd /auto-round/.azure-pipelines/scripts && bash ut/${{ parameters.utScriptFileName }}.sh"
displayName: "Run UT"
- task: PublishPipelineArtifact@1
diff --git a/.azure-pipelines/unit-test-cuda.yml b/.azure-pipelines/unit-test-cuda.yml
index 5f4420304..9db081f61 100644
--- a/.azure-pipelines/unit-test-cuda.yml
+++ b/.azure-pipelines/unit-test-cuda.yml
@@ -14,6 +14,7 @@ pr:
- setup.py
- requirements.txt
- .azure-pipelines/scripts/cuda_unit_test
+ - .azure-pipelines/scripts/ut/detect_changed_tests.sh
- .azure-pipelines/unit-test-cuda.yml
exclude:
@@ -140,6 +141,7 @@ stages:
- script: |
export UV_NO_CACHE=0
+ export FILTER_CHANGED_TESTS=true
bash .azure-pipelines/scripts/cuda_unit_test/run_cuda_ut.sh \
--test_case=ci \
--test_part=${{ pair.value.PART }}
diff --git a/.azure-pipelines/unit-test-hpu.yml b/.azure-pipelines/unit-test-hpu.yml
index 2dfd3c67d..dd07f78dc 100644
--- a/.azure-pipelines/unit-test-hpu.yml
+++ b/.azure-pipelines/unit-test-hpu.yml
@@ -14,6 +14,7 @@ pr:
- setup.py
- requirements-hpu.txt
- .azure-pipelines/scripts/ut/run_ut_hpu.sh
+ - .azure-pipelines/scripts/ut/detect_changed_tests.sh
- .azure-pipelines/template/docker-template.yml
- .azure-pipelines/template/ut-template.yml
exclude:
@@ -46,6 +47,7 @@ stages:
utScriptFileName: "run_ut_hpu"
uploadPath: $(UPLOAD_PATH)
utArtifact: "ut"
+ filterChangedTests: true
- task: UseDotNet@2
displayName: 'Use .NET Core sdk 7.0.x'
@@ -53,5 +55,6 @@ stages:
version: 7.0.x
- task: PublishCodeCoverageResults@2
+ condition: ne(variables['HAS_COVERAGE'], 'false')
inputs:
summaryFileLocation: $(UPLOAD_PATH)/coverage.xml
diff --git a/.azure-pipelines/unit-test-xpu.yml b/.azure-pipelines/unit-test-xpu.yml
index 21758e837..29acaf623 100644
--- a/.azure-pipelines/unit-test-xpu.yml
+++ b/.azure-pipelines/unit-test-xpu.yml
@@ -16,6 +16,7 @@ pr:
- .azure-pipelines/template/ut-template.yml
- .azure-pipelines/unit-test-xpu.yml
- .azure-pipelines/scripts/ut/run_ut_xpu.sh
+ - .azure-pipelines/scripts/ut/detect_changed_tests.sh
- .azure-pipelines/docker/Dockerfile_xpu.devel
- .azure-pipelines/build-auto-round-lib.yml
- .azure-pipelines/template/lib-build-template.yml
@@ -61,6 +62,7 @@ stages:
dockerFileName: $(DOCKERFILE_NAME)
utContainerName: "AutoRoundUnitTest$(NODE_LABEL)"
buildARKWheel: $(BUILD_ARK_WHEEL)
+ filterChangedTests: true
- task: UseDotNet@2
displayName: 'Use .NET Core sdk 7.0.x'
@@ -68,5 +70,6 @@ stages:
version: 7.0.x
- task: PublishCodeCoverageResults@2
+ condition: ne(variables['HAS_COVERAGE'], 'false')
inputs:
summaryFileLocation: $(UPLOAD_PATH)/coverage.xml
diff --git a/.azure-pipelines/unit-test.yml b/.azure-pipelines/unit-test.yml
index eb10a27bd..18a7bc356 100644
--- a/.azure-pipelines/unit-test.yml
+++ b/.azure-pipelines/unit-test.yml
@@ -84,6 +84,7 @@ stages:
utTestMode: $(PART)
utContainerName: "AutoRoundUnitTest$(NODE_LABEL)"
buildARKWheel: $(BUILD_ARK_WHEEL)
+ filterChangedTests: true
- stage: Coverage
displayName: "Collect Coverage"
diff --git a/.azure-pipelines/weekly-test-cuda.yml b/.azure-pipelines/weekly-test-cuda.yml
deleted file mode 100644
index a53949126..000000000
--- a/.azure-pipelines/weekly-test-cuda.yml
+++ /dev/null
@@ -1,195 +0,0 @@
-# Weekly CUDA pipeline: runs the heavy GPU integration + e2e suites
-# (vLLM / SGLang / LLMCompressor and the throughput e2e tests) that are
-# excluded from the PR CUDA unit-test pipeline. Scheduled weekly; can also be
-# triggered manually from the Azure DevOps UI.
-
-trigger: none
-pr: none
-
-schedules:
- - cron: "0 18 * * 0" # 02:00 Asia/Shanghai every Sunday
- displayName: Weekly CUDA integration + e2e run
- branches:
- include:
- - main
- always: true
-
-variables:
- - name: POOL_NAME
- value: "RunPod-GPU-Pool"
- - name: AGENT_NAME
- value: "runpod-agent-$(Build.BuildId)"
-
-parameters:
- - name: matrix
- type: object
- default:
- part0:
- PART: 0
-
-stages:
- - ${{ each pair in parameters.matrix }}:
- - stage: Start_Pod_${{ pair.key }}
- displayName: "Start Pod ${{ pair.value.PART }}"
- dependsOn: []
- jobs:
- - job: Start_Pod_Job
- displayName: "Launch Pod & Run CUDA Tests"
- timeoutInMinutes: 60
- pool:
- vmImage: "ubuntu-latest"
- steps:
- - checkout: self
-
- - task: UsePythonVersion@0
- inputs:
- versionSpec: "3.13"
- displayName: "Use Python 3.13"
-
- - task: Bash@3
- displayName: "Install dependencies"
- inputs:
- targetType: "inline"
- script: |
- pip install requests
-
- - task: Bash@3
- displayName: "Create RunPod Instance"
- name: create_runpod
- inputs:
- targetType: "inline"
- script: |
- export PYTHONUNBUFFERED=1
- cd ${BUILD_SOURCESDIRECTORY}
- CUDA_VERSION="13.0"
- python .azure-pipelines/scripts/cuda_unit_test/runpod_manager.py \
- --action create \
- --api_key $(RUNPOD_API_KEY) \
- --name "weekly-$(Build.BuildId)-${{ pair.value.PART }}" \
- --container_disk_size "100" \
- --part ${{ pair.value.PART }} \
- --cuda_version "${CUDA_VERSION}" \
- --env AZP_URL=$(System.CollectionUri) AZP_TOKEN=$(AZP_DEVOPS_PAT) AZP_POOL=$(POOL_NAME) AZP_AGENT_NAME="$(AGENT_NAME)-part${{ pair.value.PART }}"
-
- - task: Bash@3
- displayName: "Wait for Pod to be Online"
- name: wait_for_pod
- inputs:
- targetType: "inline"
- script: |
- cd ${BUILD_SOURCESDIRECTORY}
- export PYTHONUNBUFFERED=1
- python .azure-pipelines/scripts/cuda_unit_test/runpod_manager.py \
- --action wait \
- --api_key $(RUNPOD_API_KEY) \
- --name "weekly-$(Build.BuildId)-${{ pair.value.PART }}"
-
- - task: Bash@3
- displayName: "Wait for Agent to be Online"
- name: wait_for_agent
- inputs:
- targetType: "inline"
- script: |
- cd ${BUILD_SOURCESDIRECTORY}
- export PYTHONUNBUFFERED=1
- python .azure-pipelines/scripts/cuda_unit_test/azure_agent.py \
- --action wait \
- --url "$(System.CollectionUri)" \
- --pat "$(AZP_DEVOPS_PAT)" \
- --pool "$(POOL_NAME)" \
- --agent "$(AGENT_NAME)-part${{ pair.value.PART }}"
-
- - stage: GPU_Test_${{ pair.key }}
- displayName: "GPU Test ${{ pair.value.PART }}"
- dependsOn: Start_Pod_${{ pair.key }}
- jobs:
- - job: GpuTests
- timeoutInMinutes: 180
- pool:
- name: "$(POOL_NAME)"
- demands: Agent.Name -equals runpod-agent-$(Build.BuildId)-part${{ pair.value.PART }}
- steps:
- - checkout: self
- clean: true
- displayName: "Checkout Repo"
-
- - script: |
- echo "Running on GPU Agent: $(Agent.Name)"
- nvidia-smi
- lscpu
- cd .azure-pipelines/scripts/cuda_unit_test
- nohup uv run monitor_gpu.py daemon > monitor.log 2>&1 &
- displayName: "Verify GPU Access"
-
- - script: |
- echo "##[group]Installing Python dependencies..."
- uv pip install -U "pytest-cov" "pytest-html" "requests" "huggingface_hub"
- hf auth login --token "$(HF_TOKEN)"
- echo "##[endgroup]"
- displayName: "Install Python Dependencies"
-
- - script: |
- export UV_NO_CACHE=0
- bash .azure-pipelines/scripts/cuda_unit_test/run_cuda_ut.sh \
- --test_case=specific
- displayName: "Run GPU Integration + E2E Tests"
-
- - script: |
- cd .azure-pipelines/scripts/cuda_unit_test
- uv run monitor_gpu.py stop
- condition: always()
- displayName: "GPU Monitor"
-
- - stage: Cleanup_Verification_${{ pair.key }}
- displayName: "Verify Pod Cleanup ${{ pair.value.PART }}"
- dependsOn:
- - Start_Pod_${{ pair.key }}
- - GPU_Test_${{ pair.key }}
- condition: always()
- jobs:
- - job: Verify_Cleanup
- pool:
- vmImage: "ubuntu-latest"
- steps:
- - checkout: self
-
- - task: UsePythonVersion@0
- inputs:
- versionSpec: "3.13"
- displayName: "Use Python 3.13"
-
- - task: Bash@3
- displayName: "Install dependencies"
- condition: always()
- inputs:
- targetType: "inline"
- script: |
- pip install requests
-
- - task: Bash@3
- displayName: "Terminate RunPod Instance"
- condition: always()
- inputs:
- targetType: "inline"
- script: |
- echo "Terminating Pod: weekly-$(Build.BuildId)-${{ pair.value.PART }}"
- export PYTHONUNBUFFERED=1
- python .azure-pipelines/scripts/cuda_unit_test/runpod_manager.py \
- --action terminate \
- --api_key $(RUNPOD_API_KEY) \
- --name "weekly-$(Build.BuildId)-${{ pair.value.PART }}"
-
- - task: Bash@3
- displayName: "Deregister Agent from Pool"
- condition: always()
- inputs:
- targetType: "inline"
- script: |
- cd ${BUILD_SOURCESDIRECTORY}
- export PYTHONUNBUFFERED=1
- python .azure-pipelines/scripts/cuda_unit_test/azure_agent.py \
- --action deregister \
- --url "$(System.CollectionUri)" \
- --pat "$(AZP_DEVOPS_PAT)" \
- --pool "$(POOL_NAME)" \
- --agent "$(AGENT_NAME)-part${{ pair.value.PART }}"
diff --git a/test/README.md b/test/README.md
index 28947fb10..f9dddd78c 100644
--- a/test/README.md
+++ b/test/README.md
@@ -3,7 +3,7 @@
This project uses `pytest` for unit testing. All test cases are under the `test/` directory.
## 1. Environment Setup
-- Recommended Python 3.8 or above.
+- Recommended Python 3.10 or above.
- Install dependencies:
```sh
pip install -r ../requirements.txt
@@ -17,9 +17,9 @@ Tests are split into three **tiers**, then by hardware backend
- **`unit/`** — fast, self-contained tests. Run on **every PR** (`unit-test*.yml`).
- **`integration/`** — tests against third-party frameworks (vLLM, SGLang,
- LLMCompressor, INC, HuggingFace). Run **nightly** (`nightly-test*.yml`).
-- **`e2e/`** — full-model / real inference-engine tests. Run **weekly**
- (`weekly-test*.yml`).
+ LLMCompressor, INC, HuggingFace). Run **nightly** — CPU via
+ `nightly-test-cpu.yml`, XPU via `nightly-test-xpu.yml`.
+- **`e2e/`** — full-model / real inference-engine tests. Run **manually**
Within `unit/test_cpu/` and `unit/test_cuda/`, tests are grouped by functionality:
diff --git a/test/integration/README.md b/test/integration/README.md
index 6aa8b6773..100e30d67 100644
--- a/test/integration/README.md
+++ b/test/integration/README.md
@@ -19,4 +19,3 @@ These tests run in the **nightly** CI pipelines:
- CPU integration → `.azure-pipelines/nightly-test.yml`
- XPU integration → `.azure-pipelines/nightly-test-xpu.yml`
-- CUDA integration (vLLM / SGLang / LLMCompressor) → `.azure-pipelines/weekly-test-cuda.yml`
diff --git a/test/unit/test_cpu/utils/test_model_scope.py b/test/unit/test_cpu/utils/test_model_scope.py
index 17cfd497b..5d15a1247 100644
--- a/test/unit/test_cpu/utils/test_model_scope.py
+++ b/test/unit/test_cpu/utils/test_model_scope.py
@@ -30,15 +30,13 @@ class TestModelScope:
if os.path.exists(self.cache_path):
shutil.rmtree(self.cache_path, ignore_errors=True)
- @pytest.mark.skip_ci(reason="https://github.com/intel/auto-round/issues/2127")
@pytest.mark.timeout(120)
def test_llm(self, dataloader):
model_name = get_model_path("Qwen/Qwen2.5-0.5B-Instruct")
autoround = AutoRound(model_name, platform="model_scope", scheme="w4a16", iters=0, seqlen=2, dataset=dataloader)
autoround.quantize_and_save()
- @pytest.mark.skip_ci(reason="https://github.com/intel/auto-round/issues/2127")
- @pytest.mark.timeout(360)
+ @pytest.mark.timeout(480)
def test_mllm(self, dataloader):
model_name = get_model_path("Qwen/Qwen2-VL-2B-Instruct")
autoround = AutoRound(