[NPU][CI] Add CANN 9.1.0 and Ascend a5 nightly suites (#38833)

This commit is contained in:
pllimax
2026-09-14 22:39:42 +08:00
committed by GitHub
parent 433c999dd0
commit 7465e42b7a
8 changed files with 323 additions and 135 deletions
@@ -345,6 +345,7 @@ jobs:
source /usr/local/Ascend/nnal/atb/set_env.sh || true
source /usr/local/Ascend/ascend-toolkit/latest/opp/vendors/customize/bin/set_env.bash || true
source /usr/local/Ascend/ascend-toolkit/latest/opp/vendors/custom_transformer/bin/set_env.bash || true
source /usr/local/Ascend/ascend-toolkit/latest/set_env.sh || true
set -u
# Nightly log path mirrors the output layout; PR keeps the original {date}/{testcase}.
+166 -3
View File
@@ -29,6 +29,16 @@ on:
required: false
type: string
default: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/dockerhub/lmsysorg/sglang:main-cann9.0.0-a3'
image_a3_cann910:
description: 'The a3 running docker image of the test task with cann 9.1.0.'
required: false
type: string
default: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/dockerhub/lmsysorg/sglang:cann9.1.0-a3-nightly'
image_a5:
description: 'The a5 running docker image of the test task.'
required: false
type: string
default: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/dockerhub/lmsysorg/sglang:cann9.1.0-950-nightly'
skip_install_flag:
description: 'Indicates whether to skip the installation of sglang, defaulting to false.'
required: false
@@ -56,6 +66,16 @@ on:
required: false
type: string
default: ''
image_a3_cann910:
description: 'The a3 running docker image of the test task with cann 9.1.0.'
required: false
type: string
default: ''
image_a5:
description: 'The a5 running docker image of the test task.'
required: false
type: string
default: ''
skip_install_flag:
description: 'Indicates whether to skip the installation of sglang, defaulting to false.'
required: false
@@ -72,6 +92,8 @@ jobs:
job_filter: ${{ steps.set-vars.outputs.job_filter }}
image_a2: ${{ steps.set-vars.outputs.image_a2 }}
image_a3: ${{ steps.set-vars.outputs.image_a3 }}
image_a3_cann910: ${{ steps.set-vars.outputs.image_a3_cann910 }}
image_a5: ${{ steps.set-vars.outputs.image_a5 }}
skip_install_flag: ${{ steps.set-vars.outputs.skip_install_flag }}
run_start_metadata: ${{ steps.set-vars.outputs.run_start_metadata }}
steps:
@@ -103,6 +125,16 @@ jobs:
else
echo "image_a3=${{ inputs.image_a3 }}" >> $GITHUB_OUTPUT
fi
if [ -z "${{ inputs.image_a3_cann910 }}" ]; then
echo "image_a3_cann910=swr.cn-southwest-2.myhuaweicloud.com/base_image/dockerhub/lmsysorg/sglang:cann9.1.0-a3-nightly" >> $GITHUB_OUTPUT
else
echo "image_a3_cann910=${{ inputs.image_a3_cann910 }}" >> $GITHUB_OUTPUT
fi
if [ -z "${{ inputs.image_a5 }}" ]; then
echo "image_a5=swr.cn-southwest-2.myhuaweicloud.com/base_image/dockerhub/lmsysorg/sglang:cann9.1.0-950-nightly" >> $GITHUB_OUTPUT
else
echo "image_a5=${{ inputs.image_a5 }}" >> $GITHUB_OUTPUT
fi
if [ -z "${{ inputs.skip_install_flag }}" ]; then
echo "skip_install_flag=false" >> $GITHUB_OUTPUT
else
@@ -282,6 +314,56 @@ jobs:
device_type_for_deps: 'a3'
run_start_metadata: ${{ needs.set-image-config.outputs.run_start_metadata }}
nightly-acc-4-npu-a5:
name: nightly-acc-4-npu-a5
if: ${{ !cancelled() }}
needs: [set-image-config]
uses: ./.github/workflows/_npu-single-node-test-stage.yml
with:
runner: linux-amd64-a5-4
test_type: 'accuracy'
test_suite: nightly-acc-4-npu-a5
is_nightly_pipeline_job: true
skip_pr_test_health_check: 'true'
image: ${{ needs.set-image-config.outputs.image_a5 }}
install_sglang_deps: false
device_type_for_deps: 'a5'
run_start_metadata: ${{ needs.set-image-config.outputs.run_start_metadata }}
# Suites suffixed with `-cann910` run against the CANN 9.1.0 image.
nightly-perf-16-npu-a3-cann910:
name: nightly-perf-16-npu-a3-cann910
if: ${{ !cancelled() }}
needs: [set-image-config]
uses: ./.github/workflows/_npu-single-node-test-stage.yml
with:
runner: linux-aarch64-a3-800t-16
test_type: 'perf'
test_suite: nightly-perf-16-npu-a3-cann910
is_nightly_pipeline_job: true
skip_pr_test_health_check: 'true'
image: ${{ needs.set-image-config.outputs.image_a3_cann910 }}
install_sglang_deps: false
device_type_for_deps: 'a3'
run_start_metadata: ${{ needs.set-image-config.outputs.run_start_metadata }}
test_timeout_minutes: '180'
nightly-acc-16-npu-a3-cann910:
name: nightly-acc-16-npu-a3-cann910
if: ${{ !cancelled() }}
needs: [set-image-config]
uses: ./.github/workflows/_npu-single-node-test-stage.yml
with:
runner: linux-aarch64-a3-16-
test_type: 'accuracy'
test_suite: nightly-acc-16-npu-a3-cann910
is_nightly_pipeline_job: true
skip_pr_test_health_check: 'true'
image: ${{ needs.set-image-config.outputs.image_a3_cann910 }}
install_sglang_deps: false
device_type_for_deps: 'a3'
run_start_metadata: ${{ needs.set-image-config.outputs.run_start_metadata }}
nightly-poc-multi-node-tests:
name: multi-node-poc
if: ${{ !cancelled() }}
@@ -362,6 +444,72 @@ jobs:
transformers_version: ''
run_start_metadata: ${{ needs.set-image-config.outputs.run_start_metadata }}
nightly-poc-multi-node-tests-cann910:
name: multi-node-poc-cann910
if: ${{ !cancelled() }}
# Multi-node jobs run strictly one at a time to avoid contending for the
# same A3 multi-node resources: 9.0.0 multi -> 9.0.0 mix -> cann910 multi -> cann910 mix.
needs: [set-image-config, nightly-perf-16-npu-a3-cann910, nightly-acc-16-npu-a3-cann910, nightly-poc-multi-node-tests, nightly-poc-multi-node-mix-tests]
strategy:
fail-fast: false
max-parallel: 1
matrix:
test_config:
# deepseek_v4_flash performance tests
- name: deepseek_v4_flash_w8a8_1p1d_16p_in8k_out1k_50ms
prefill_size: 1
decode_size: 1
router_size: 1
test_case: test/registered/npu/performance/deepseek_v4_flash/test_npu_deepseek_v4_flash_w8a8_1p1d_16p_in8k_out1k_50ms.py
test_type: 'perf'
prefill_decode_deployment: 'separation'
uses: ./.github/workflows/nightly-test-npu-e2e-multi-node.yml
with:
runner: linux-amd64-cpu-4
test_type: ${{ matrix.test_config.test_type || 'perf' }}
test_config_name: ${{ matrix.test_config.name }}
prefill_size: ${{ matrix.test_config.prefill_size }}
decode_size: ${{ matrix.test_config.decode_size }}
router_size: ${{ matrix.test_config.router_size }}
test_case: ${{ matrix.test_config.test_case }}
image: ${{ needs.set-image-config.outputs.image_a3_cann910 }}
install_sglang_from_source: false
prefill_decode_deployment: ${{ matrix.test_config.prefill_decode_deployment }}
transformers_version: ''
run_start_metadata: ${{ needs.set-image-config.outputs.run_start_metadata }}
nightly-poc-multi-node-mix-tests-cann910:
name: multi-node-mix-poc-cann910
if: ${{ !cancelled() }}
needs: [set-image-config, nightly-poc-multi-node-tests-cann910]
strategy:
fail-fast: false
max-parallel: 1
matrix:
test_config:
# glm_5_2 accuracy tests
- name: glm_5_2_w4a8_16p_gpqa
node_size: 2
test_case: test/registered/npu/accuracy/glm5_2/test_npu_glm_5_2_w4a8_16p_gpqa.py
test_type: 'accuracy'
# kimi_k3 accuracy tests
- name: kimi_k3_w4a8_32p_gpqa
node_size: 4
test_case: test/registered/npu/accuracy/kimi_k3/test_npu_kimi_k3_w4a8_32p_gpqa.py
test_type: 'accuracy'
uses: ./.github/workflows/nightly-test-npu-e2e-multi-node.yml
with:
runner: linux-amd64-cpu-4
test_type: ${{ matrix.test_config.test_type || 'perf' }}
test_config_name: ${{ matrix.test_config.name }}
node_size: ${{ matrix.test_config.node_size }}
test_case: ${{ matrix.test_config.test_case }}
image: ${{ needs.set-image-config.outputs.image_a3_cann910 }}
install_sglang_from_source: false
prefill_decode_deployment: 'mix'
transformers_version: ''
run_start_metadata: ${{ needs.set-image-config.outputs.run_start_metadata }}
check-all-jobs:
if: ${{ !cancelled() }}
needs:
@@ -375,14 +523,21 @@ jobs:
- nightly-perf-16-npu-a3
- nightly-acc-2-npu-a3
- nightly-acc-16-npu-a3
- nightly-perf-16-npu-a3-cann910
- nightly-acc-16-npu-a3-cann910
- nightly-acc-4-npu-a5
- nightly-poc-multi-node-tests
- nightly-poc-multi-node-mix-tests
- nightly-poc-multi-node-tests-cann910
- nightly-poc-multi-node-mix-tests-cann910
runs-on: ubuntu-latest
steps:
- name: Generate results table
run: |
multi_result="${{ needs.nightly-poc-multi-node-tests.result }}"
mix_result="${{ needs.nightly-poc-multi-node-mix-tests.result }}"
multi_cann910_result="${{ needs.nightly-poc-multi-node-tests-cann910.result }}"
mix_cann910_result="${{ needs.nightly-poc-multi-node-mix-tests-cann910.result }}"
# single-node suites are reported per suite; overall status is success if none failed
single_result="success"
@@ -396,7 +551,10 @@ jobs:
"${{ needs.nightly-perf-4-npu-a3.result }}" \
"${{ needs.nightly-perf-16-npu-a3.result }}" \
"${{ needs.nightly-acc-2-npu-a3.result }}" \
"${{ needs.nightly-acc-16-npu-a3.result }}"; do
"${{ needs.nightly-acc-16-npu-a3.result }}" \
"${{ needs.nightly-perf-16-npu-a3-cann910.result }}" \
"${{ needs.nightly-acc-16-npu-a3-cann910.result }}" \
"${{ needs.nightly-acc-4-npu-a5.result }}"; do
if [ "${r}" != "success" ] && [ "${r}" != "skipped" ]; then
single_result="failure"
fi
@@ -426,17 +584,22 @@ jobs:
"nightly-perf-4-npu-a3:${{ needs.nightly-perf-4-npu-a3.result }}" \
"nightly-perf-16-npu-a3:${{ needs.nightly-perf-16-npu-a3.result }}" \
"nightly-acc-2-npu-a3:${{ needs.nightly-acc-2-npu-a3.result }}" \
"nightly-acc-16-npu-a3:${{ needs.nightly-acc-16-npu-a3.result }}"; do
"nightly-acc-16-npu-a3:${{ needs.nightly-acc-16-npu-a3.result }}" \
"nightly-perf-16-npu-a3-cann910:${{ needs.nightly-perf-16-npu-a3-cann910.result }}" \
"nightly-acc-16-npu-a3-cann910:${{ needs.nightly-acc-16-npu-a3-cann910.result }}" \
"nightly-acc-4-npu-a5:${{ needs.nightly-acc-4-npu-a5.result }}"; do
suite="${entry%%:*}"
r="${entry##*:}"
echo "| ${suite} | $(group_icon ${r}) ${r} |" >> $GITHUB_STEP_SUMMARY
done
echo "| multi-node-poc | $(group_icon ${multi_result}) ${multi_result} |" >> $GITHUB_STEP_SUMMARY
echo "| multi-node-mix-poc | $(group_icon ${mix_result}) ${mix_result} |" >> $GITHUB_STEP_SUMMARY
echo "| multi-node-poc-cann910 | $(group_icon ${multi_cann910_result}) ${multi_cann910_result} |" >> $GITHUB_STEP_SUMMARY
echo "| multi-node-mix-poc-cann910 | $(group_icon ${mix_cann910_result}) ${mix_cann910_result} |" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
FAIL=0
for r in "${single_result}" "${multi_result}" "${mix_result}"; do
for r in "${single_result}" "${multi_result}" "${mix_result}" "${multi_cann910_result}" "${mix_cann910_result}"; do
if [ "${r}" != "success" ] && [ "${r}" != "skipped" ]; then FAIL=1; fi
done
exit $FAIL