### What this PR does / why we need it?
1.fix "TypeError: get_attn_backend() remove variable": [Refactor
`check_and_update_config`](https://github.com/vllm-project/vllm/pull/35122)
2.fix [Rename `compile_ranges_split_points` to
`compile_ranges_endpoints`](https://github.com/vllm-project/vllm/pull/36027)
3.fix "RuntimeError: device_allocator not a DeviceAllocator":[Replace
memory related torch.cuda
APIs"](https://github.com/vllm-project/vllm/pull/37031)
4.fix [Support multiple KV groups in OffloadingSpec
](https://github.com/vllm-project/vllm/pull/36610) removed
self.offloaded_block_size and changed self.gpu_block_size from a scalar
to a tuple of per-group block sizes, adding block_size_factor.
5.fix [Consolidate
SupportsEagle](https://github.com/vllm-project/vllm/pull/36063) renamed
get_eagle3_aux_hidden_state_layers() to
get_eagle3_default_aux_hidden_state_layers() and added a
supports_eagle3() guard before calling it.
### Does this PR introduce _any_ user-facing change?
NA
### How was this patch tested?
E2E
- vLLM version: v0.17.0
- vLLM main:
8a680463fa
---------
Signed-off-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Claude Code <noreply@anthropic.com>
116 lines
4.3 KiB
YAML
116 lines
4.3 KiB
YAML
#
|
|
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
# This file is a part of the vllm-ascend project.
|
|
#
|
|
|
|
name: E2E-Light
|
|
|
|
on:
|
|
pull_request:
|
|
branches:
|
|
- 'main'
|
|
- '*-dev'
|
|
- 'releases/v*'
|
|
|
|
# Bash shells do not use ~/.profile or ~/.bashrc so these shells need to be explicitly
|
|
# declared as "shell: bash -el {0}" on steps that need to be properly activated.
|
|
# It's used to activate ascend-toolkit environment variables.
|
|
defaults:
|
|
run:
|
|
shell: bash -el {0}
|
|
|
|
# only cancel in-progress runs of the same workflow
|
|
# and ignore the lint / 1 card / 4 cards test type
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
lint:
|
|
uses: ./.github/workflows/_pre_commit.yml
|
|
with:
|
|
vllm: 8a680463fab3bc9e6760417cd5c0a6aa58283065
|
|
changes:
|
|
runs-on: linux-aarch64-a2b3-0
|
|
outputs:
|
|
e2e_tracker: ${{ steps.filter.outputs.e2e_tracker }}
|
|
ut_tracker: ${{ steps.filter.outputs.ut_tracker }}
|
|
_310_tracker: ${{ steps.filter.outputs._310_tracker }}
|
|
steps:
|
|
- name: Setup git proxy
|
|
run: |
|
|
git config --global --add safe.directory "$GITHUB_WORKSPACE"
|
|
git config --global url."https://gh-proxy.test.osinfra.cn/https://github.com/".insteadOf https://github.com/
|
|
# NOTE: Do not update the version of checkout, there have some issue on self_hosted runner with the higher version
|
|
- uses: actions/checkout@v6
|
|
- uses: dorny/paths-filter@v3
|
|
id: filter
|
|
with:
|
|
filters: |
|
|
e2e_tracker:
|
|
- '.github/workflows/pr_test_light.yaml'
|
|
- '.github/workflows/_e2e_test.yaml'
|
|
- 'vllm_ascend/**'
|
|
- 'csrc/**'
|
|
- 'cmake/**'
|
|
- 'tests/e2e/**'
|
|
- 'CMakeLists.txt'
|
|
- 'setup.py'
|
|
- 'requirements.txt'
|
|
- 'requirements-dev.txt'
|
|
- 'requirements-lint.txt'
|
|
- 'packages.txt'
|
|
ut_tracker:
|
|
- 'tests/ut/**'
|
|
- '.github/workflows/pr_test_light.yaml'
|
|
_310_tracker:
|
|
- 'vllm_ascend/_310p/**'
|
|
- 'tests/e2e/310p/**'
|
|
- 'vllm_ascend/worker/model_runner_v1.py'
|
|
- 'vllm_ascend/attention/attention_v1.py'
|
|
- 'vllm_ascend/ops/fused_moe/**'
|
|
- 'CMakeLists.txt'
|
|
|
|
ut:
|
|
needs: [lint, changes]
|
|
name: unit test
|
|
# only trigger unit test after lint passed and the change is e2e and ut related.
|
|
if: ${{ needs.lint.result == 'success' && (needs.changes.outputs.e2e_tracker == 'true' || needs.changes.outputs.ut_tracker == 'true') }}
|
|
strategy:
|
|
matrix:
|
|
vllm_version: [8a680463fab3bc9e6760417cd5c0a6aa58283065, v0.17.0]
|
|
uses: ./.github/workflows/_unit_test.yaml
|
|
with:
|
|
vllm: ${{ matrix.vllm_version }}
|
|
runner: linux-amd64-cpu-8-hk
|
|
image: quay.nju.edu.cn/ascend/cann:8.5.1-910b-ubuntu22.04-py3.11
|
|
type: pr
|
|
|
|
e2e-light:
|
|
name: e2e-light
|
|
strategy:
|
|
matrix:
|
|
vllm_version: [8a680463fab3bc9e6760417cd5c0a6aa58283065, v0.17.0]
|
|
# Note (yikun): If CI resource are limited we can split job into two chain jobs
|
|
needs: [lint, changes]
|
|
# only trigger e2e test after lint passed and the change is e2e related with pull request.
|
|
if: ${{ github.event_name == 'pull_request' && needs.lint.result == 'success' && needs.changes.outputs.e2e_tracker == 'true' && !contains(github.event.pull_request.labels.*.name, 'ready') }}
|
|
uses: ./.github/workflows/_e2e_test.yaml
|
|
with:
|
|
vllm: ${{ matrix.vllm_version }}
|
|
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.1-910b-ubuntu22.04-py3.11
|
|
contains_310: ${{ needs.changes.outputs._310_tracker == 'true' }}
|
|
type: light
|