Fix accuracy test config and add DeepSeek-V2-Lite test (#2261)
### What this PR does / why we need it?
This PR fix accuracy test related to
https://github.com/vllm-project/vllm-ascend/pull/2073, users can now
perform accuracy tests on multiple models simultaneously and generate
different report files by running:
```bash
cd ~/vllm-ascend
pytest -sv ./tests/e2e/models/test_lm_eval_correctness.py \
--config-list-file ./tests/e2e/models/configs/accuracy.txt
```
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
<img width="1648" height="511" alt="image"
src="https://github.com/user-attachments/assets/1757e3b8-a6b7-44e5-b701-80940dc756cd"
/>
- vLLM version: v0.10.0
- vLLM main:
766bc8162c
---------
Signed-off-by: Icey <1790571317@qq.com>
This commit is contained in:
Icey
9
.github/workflows/accuracy_test.yaml
vendored
9
.github/workflows/accuracy_test.yaml
vendored
@@ -70,6 +70,8 @@ jobs:
|
||||
runner: linux-aarch64-a2-1
|
||||
- model_name: Qwen3-30B-A3B
|
||||
runner: linux-aarch64-a2-2
|
||||
- model_name: DeepSeek-V2-Lite
|
||||
runner: linux-aarch64-a2-2
|
||||
fail-fast: false
|
||||
|
||||
name: ${{ matrix.model_name }} accuracy
|
||||
@@ -200,9 +202,8 @@ jobs:
|
||||
markdown_name="${model_base_name}"
|
||||
echo "markdown_name=$markdown_name" >> $GITHUB_OUTPUT
|
||||
mkdir -p ./benchmarks/accuracy
|
||||
pytest -sv ./tests/e2e/singlecard/models/test_lm_eval_correctness.py \
|
||||
--config ./tests/e2e/singlecard/models/configs/${{ matrix.model_name }}.yaml \
|
||||
--report_output ./benchmarks/accuracy/${model_base_name}.md
|
||||
pytest -sv ./tests/e2e/models/test_lm_eval_correctness.py \
|
||||
--config ./tests/e2e/models/configs/${{ matrix.model_name }}.yaml
|
||||
|
||||
- name: Generate step summary
|
||||
if: ${{ always() }}
|
||||
@@ -312,7 +313,7 @@ jobs:
|
||||
head: `vllm-ascend-ci:${{ env.BRANCH_NAME }}`,
|
||||
base: '${{ github.event.inputs.vllm-ascend-version }}',
|
||||
title: `[Doc] Update accuracy reports for ${{ github.event.inputs.vllm-ascend-version }}`,
|
||||
body: `The accuracy results running on NPU Altlas A2 have changed, updating reports for: All models (Qwen/Qwen3-30B-A3B, Qwen2.5-VL-7B-Instruct, Qwen3-8B-Base)
|
||||
body: `The accuracy results running on NPU Altlas A2 have changed, updating reports for: All models (Qwen3-30B-A3B, Qwen2.5-VL-7B-Instruct, Qwen3-8B-Base, DeepSeek-V2-Lite)
|
||||
|
||||
- [Workflow run][1]
|
||||
|
||||
|
||||
3
.github/workflows/vllm_ascend_test.yaml
vendored
3
.github/workflows/vllm_ascend_test.yaml
vendored
@@ -211,8 +211,7 @@ jobs:
|
||||
--ignore=tests/e2e/singlecard/test_embedding.py \
|
||||
--ignore=tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py \
|
||||
--ignore=tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py \
|
||||
--ignore=tests/e2e/singlecard/test_offline_inference_310p.py \
|
||||
--ignore=tests/e2e/singlecard/models/test_lm_eval_correctness.py
|
||||
--ignore=tests/e2e/singlecard/test_offline_inference_310p.py
|
||||
e2e-2-cards:
|
||||
needs: [e2e]
|
||||
if: ${{ needs.e2e.result == 'success' }}
|
||||
|
||||
102
.github/workflows/vllm_ascend_test_long_term.yaml
vendored
102
.github/workflows/vllm_ascend_test_long_term.yaml
vendored
@@ -1,102 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
|
||||
# This file is a part of the vllm-ascend project.
|
||||
#
|
||||
# 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.
|
||||
#
|
||||
name: 'e2e test / long-term-test'
|
||||
|
||||
on:
|
||||
schedule:
|
||||
# Runs at 23:00 UTC (7:00 AM Beijing) every day
|
||||
- cron: '0 23 * * *'
|
||||
pull_request:
|
||||
types: [ labeled ]
|
||||
|
||||
# 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
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
long-term-test:
|
||||
# long-term-test will be triggered when tag 'long-term-test' & 'ready-for-test' or schedule job
|
||||
if: ${{ contains(github.event.pull_request.labels.*.name, 'long-term-test') && contains(github.event.pull_request.labels.*.name, 'ready-for-test') || github.event_name == 'schedule' }}
|
||||
strategy:
|
||||
max-parallel: 2
|
||||
matrix:
|
||||
os: [linux-aarch64-a2-1, linux-aarch64-a2-2]
|
||||
vllm_version: [main, v0.10.0]
|
||||
name: vLLM Ascend long term test
|
||||
runs-on: ${{ matrix.os }}
|
||||
container:
|
||||
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
|
||||
env:
|
||||
VLLM_LOGGING_LEVEL: ERROR
|
||||
VLLM_USE_MODELSCOPE: True
|
||||
steps:
|
||||
- name: Check npu and CANN info
|
||||
run: |
|
||||
npu-smi info
|
||||
cat /usr/local/Ascend/ascend-toolkit/latest/"$(uname -i)"-linux/ascend_toolkit_install.info
|
||||
|
||||
- name: Config mirrors
|
||||
run: |
|
||||
sed -Ei 's@(ports|archive).ubuntu.com@cache-service.nginx-pypi-cache.svc.cluster.local:8081@g' /etc/apt/sources.list
|
||||
pip config set global.index-url http://cache-service.nginx-pypi-cache.svc.cluster.local/pypi/simple
|
||||
pip config set global.trusted-host cache-service.nginx-pypi-cache.svc.cluster.local
|
||||
apt-get update -y
|
||||
apt install git -y
|
||||
|
||||
- name: Checkout vllm-project/vllm-ascend repo
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install system dependencies
|
||||
run: |
|
||||
apt-get -y install `cat packages.txt`
|
||||
apt-get -y install gcc g++ cmake libnuma-dev
|
||||
|
||||
- name: Checkout vllm-project/vllm repo
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
repository: vllm-project/vllm
|
||||
ref: ${{ matrix.vllm_version }}
|
||||
path: ./vllm-empty
|
||||
|
||||
- name: Install vllm-project/vllm from source
|
||||
working-directory: ./vllm-empty
|
||||
run: |
|
||||
VLLM_TARGET_DEVICE=empty pip install -e .
|
||||
|
||||
- name: Install vllm-project/vllm-ascend
|
||||
env:
|
||||
PIP_EXTRA_INDEX_URL: https://mirrors.huaweicloud.com/ascend/repos/pypi
|
||||
run: |
|
||||
pip install -r requirements-dev.txt
|
||||
pip install -v -e .
|
||||
|
||||
- name: Run vllm-project/vllm-ascend long term test
|
||||
run: |
|
||||
if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then
|
||||
pytest -sv tests/e2e/long_term/accuracy/accuracy_singlecard.py
|
||||
else
|
||||
# accuracy test multi card
|
||||
pytest -sv tests/e2e/long_term/accuracy/accuracy_multicard.py
|
||||
fi
|
||||
Reference in New Issue
Block a user