[CI] Refactor CI (#952)
1. remove some useless test func and file 2. fix format.sh problem 3. enable full test for singlecard and multicard 4. move long term test to long_term folder. For this kind of test, it only runs by labeled and daily test. Include: spec decode、accuracy test ## After refactor: There are 4 test modules - `singlecard`: contains the test running on one NPU. It'll be run for each PR and daily test. - `multicard`: contains the test running on multi NPUs. It'll be run for each PR and daily test. - `long_term`: contains the test that cost much time(Now include `spec decode` and `accuracy` test). It'll be run for the PR with `long-term-test` labeled and daily test. - `e2e`: contains the test for doc and pd feature. It'll be run for the PR with `pd-test` labeled and daily test. ## Todo: 1. some test are skipped, they should be fixed and reenabled in the future. 2. pyhccl test for multicard doesn't work at all. It should be enabled as well. 3. ensure long-term-test pass by daily test. ### Know issue Now, `ready` labels is required to start pd test or long term test. And when `long-term-test` or `pd-test` is labeled after another one, the old labeled test will be re-run again. So the labeled test should be ran in the following step: 1. decide which test need run, then label it. `long-term-test` or `pd-test` or both. 2. add `ready-for-test` label, then the test will be ran. Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
78
.github/workflows/vllm_ascend_test.yaml
vendored
78
.github/workflows/vllm_ascend_test.yaml
vendored
@@ -30,7 +30,6 @@ on:
|
||||
- '.github/workflows/vllm_ascend_test.yaml'
|
||||
- '!docs/**'
|
||||
- 'pytest.ini'
|
||||
|
||||
# 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.
|
||||
@@ -38,24 +37,20 @@ defaults:
|
||||
run:
|
||||
shell: bash -el {0}
|
||||
|
||||
concurrency:
|
||||
group: pr-${{ github.event.pull_request.number }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
test:
|
||||
strategy:
|
||||
max-parallel: 2
|
||||
matrix:
|
||||
os: [linux-arm64-npu-1, linux-arm64-npu-4]
|
||||
vllm_verison: [main, v0.8.5.post1]
|
||||
vllm_version: [main, v0.8.5.post1]
|
||||
concurrency:
|
||||
group: >
|
||||
${{
|
||||
matrix.os == 'linux-arm64-npu-4'
|
||||
&& github.event.pull_request.number
|
||||
&& format('pr-{0}-limit-npu-4', github.event.pull_request.number)
|
||||
|| format('job-{0}-{1}-{2}', matrix.os, matrix.vllm_verison, github.event.pull_request.number)
|
||||
|| format('job-{0}-{1}-{2}', matrix.os, matrix.vllm_version, github.event.pull_request.number)
|
||||
}}
|
||||
cancel-in-progress: false
|
||||
name: vLLM Ascend test
|
||||
@@ -66,6 +61,7 @@ jobs:
|
||||
env:
|
||||
HF_ENDPOINT: https://hf-mirror.com
|
||||
HF_TOKEN: ${{ secrets.HF_TOKEN }}
|
||||
VLLM_LOGGING_LEVEL: ERROR
|
||||
steps:
|
||||
- name: Check npu and CANN info
|
||||
run: |
|
||||
@@ -92,7 +88,7 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
repository: vllm-project/vllm
|
||||
ref: ${{ matrix.vllm_verison }}
|
||||
ref: ${{ matrix.vllm_version }}
|
||||
path: ./vllm-empty
|
||||
|
||||
- name: Install vllm-project/vllm from source
|
||||
@@ -111,15 +107,15 @@ jobs:
|
||||
VLLM_WORKER_MULTIPROC_METHOD: spawn
|
||||
run: |
|
||||
if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then
|
||||
pytest -sv tests/singlecard/test_offline_inference.py
|
||||
pytest -sv tests/singlecard/test_ilama_lora.py
|
||||
pytest -sv tests/ops
|
||||
pytest -sv tests/compile
|
||||
VLLM_USE_MODELSCOPE=True pytest -sv tests/singlecard/test_offline_inference.py
|
||||
# AscendScheduler doesn't work, fix it later
|
||||
# pytest -sv tests/singlecard/tets_schedule.py
|
||||
# guided decoding doesn't work, fix it later
|
||||
# pytest -sv tests/singlecard/test_guided_decoding.py.py
|
||||
pytest -sv tests/singlecard/ --ignore=tests/singlecard/test_offline_inference.py --ignore=tests/singlecard/test_scheduler.py --ignore=tests/singlecard/test_guided_decoding.py
|
||||
else
|
||||
pytest -sv -k "QwQ" tests/multicard/test_offline_inference_distributed.py
|
||||
pytest -sv tests/multicard/test_ilama_lora_tp2.py
|
||||
pytest -sv tests/ops
|
||||
pytest -sv tests/compile
|
||||
VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/ --ignore=tests/multicard/test_ilama_lora_tp2.py
|
||||
fi
|
||||
|
||||
- name: Run vllm-project/vllm-ascend test on V0 engine
|
||||
@@ -127,48 +123,16 @@ jobs:
|
||||
VLLM_USE_V1: 0
|
||||
run: |
|
||||
if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then
|
||||
pytest -sv tests/singlecard/test_ilama_lora.py
|
||||
pytest -sv tests/singlecard/test_offline_inference.py
|
||||
pytest -sv tests/ops
|
||||
VLLM_USE_MODELSCOPE=True pytest -sv tests/singlecard/test_offline_inference.py
|
||||
# AscendScheduler doesn't work, fix it later
|
||||
# pytest -sv tests/singlecard/tets_schedule.py
|
||||
# guided decoding doesn't work, fix it later
|
||||
# pytest -sv tests/singlecard/test_guided_decoding.py.py
|
||||
pytest -sv tests/singlecard/ --ignore=tests/singlecard/test_offline_inference.py --ignore=tests/singlecard/test_scheduler.py --ignore=tests/singlecard/test_guided_decoding.py
|
||||
else
|
||||
pytest -sv tests/multicard/test_ilama_lora_tp2.py
|
||||
pytest -sv -k "QwQ" tests/multicard/test_offline_inference_distributed.py
|
||||
pytest -sv -k "DeepSeek" tests/multicard/test_offline_inference_distributed.py
|
||||
pytest -sv tests/ops
|
||||
# Fixme: run VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py will raise error.
|
||||
VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py::test_models_distributed_QwQ
|
||||
VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek
|
||||
VLLM_USE_MODELSCOPE=True pytest -sv tests/multicard/ --ignore=tests/multicard/test_ilama_lora_tp2.py --ignore=tests/multicard/test_offline_inference_distributed.py
|
||||
fi
|
||||
|
||||
# only run test on spec decode when the related code changed
|
||||
- name: Check for changes in Speculative Decode
|
||||
if: github.event_name != 'schedule'
|
||||
id: filter_spec_decode
|
||||
uses: dorny/paths-filter@v3
|
||||
with:
|
||||
filters: |
|
||||
speculative_tests_changed:
|
||||
- ".github/workflows/vllm_ascend_test.yaml"
|
||||
- "tests/singlecard/spec_decode/**"
|
||||
- "tests/multicard/spec_decode_e2e/**"
|
||||
- "vllm_ascend/worker/worker.py"
|
||||
- "vllm_ascend/worker/model_runner.py"
|
||||
- "vllm_ascend/worker/multi_step_runner.py"
|
||||
- "vllm_ascend/worker/multi_step_worker.py"
|
||||
- "vllm_ascend/worker/draft_model_runner.py"
|
||||
- "vllm_ascend/patch/worker/patch_common/patch_metrics.py"
|
||||
- "vllm_ascend/patch/worker/patch_common/patch_spec_decode_worker.py"
|
||||
- "vllm_ascend/patch/worker/patch_common/patch_multi_step_worker.py"
|
||||
|
||||
- name: Run vllm-project/vllm-ascend Speculative Decode test
|
||||
if: steps.filter_spec_decode.outputs.speculative_tests_changed == 'true' || github.event_name == 'schedule'
|
||||
run: |
|
||||
if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then
|
||||
VLLM_USE_MODELSCOPE=true pytest -sv tests/singlecard/spec_decode/e2e/test_v1_spec_decode.py
|
||||
pytest -sv tests/singlecard/spec_decode/e2e/test_mtp_correctness.py # it needs a clean process
|
||||
pytest -sv tests/singlecard/spec_decode --ignore=tests/singlecard/spec_decode/e2e/test_mtp_correctness.py --ignore=tests/singlecard/spec_decode/e2e/test_v1_spec_decode.py
|
||||
fi
|
||||
|
||||
- name: Run vllm-project/vllm test for V0 Engine
|
||||
env:
|
||||
VLLM_USE_V1: 0
|
||||
PYTORCH_NPU_ALLOC_CONF: max_split_size_mb:256
|
||||
run: |
|
||||
pytest -sv
|
||||
|
||||
Reference in New Issue
Block a user