Files
xc-llm-ascend/.github/workflows/schedule_nightly_test_a3.yaml
SILONG ZENG 859f2c25b9 [Nightly][Refactor]Migrate nightly single-node model tests from .py to .yaml (#6503)
### What this PR does / why we need it?
This PR refactors the nightly single-node model test by migrating test
configurations from Python scripts to a more maintainable `YAML-based`
format.

| Original PR | Python (`.py`) | YAML (`.yaml`) |
| :--- | :--- | :--- |
| [#3568](https://github.com/vllm-project/vllm-ascend/pull/3568) |
`test_deepseek_r1_0528_w8a8_eplb.py` | `DeepSeek-R1-0528-W8A8.yaml` |
| [#3631](https://github.com/vllm-project/vllm-ascend/pull/3631) |
`test_deepseek_r1_0528_w8a8.py` | `DeepSeek-R1-0528-W8A8.yaml` |
| [#5874](https://github.com/vllm-project/vllm-ascend/pull/5874) |
`test_deepseek_r1_w8a8_hbm.py` | `DeepSeek-R1-W8A8-HBM.yaml` |
| [#3908](https://github.com/vllm-project/vllm-ascend/pull/3908) |
`test_deepseek_v3_2_w8a8.py` | `DeepSeek-V3.2-W8A8.yaml` |
| [#5682](https://github.com/vllm-project/vllm-ascend/pull/5682) |
`test_kimi_k2_thinking.py` | `Kimi-K2-Thinking.yaml` |
| [#4111](https://github.com/vllm-project/vllm-ascend/pull/4111) |
`test_mtpx_deepseek_r1_0528_w8a8.py` | `MTPX-DeepSeek-R1-0528-W8A8.yaml`
|
| [#3733](https://github.com/vllm-project/vllm-ascend/pull/3733) |
`test_prefix_cache_deepseek_r1_0528_w8a8.py` |
`Prefix-Cache-DeepSeek-R1-0528-W8A8.yaml` |
| [#6543](https://github.com/vllm-project/vllm-ascend/pull/6543) |
`test_qwen3_235b_w8a8.py` | `Qwen3-235B-A22B-W8A8.yaml` |
| [#6543](https://github.com/vllm-project/vllm-ascend/pull/6543) |
`test_qwen3_235b_a22b_w8a8_eplb.py` | `Qwen3-235B-A22B-W8A8.yaml` |
| [#3973](https://github.com/vllm-project/vllm-ascend/pull/3973) |
`test_qwen3_30b_w8a8.py` | `Qwen3-30B-A3B-W8A8.yaml` |
| [#3541](https://github.com/vllm-project/vllm-ascend/pull/3541) |
`test_qwen3_32b_int8.py` | `Qwen3-32B-Int8.yaml` |
| [#3757](https://github.com/vllm-project/vllm-ascend/pull/3757) |
`test_qwq_32b.py` | `QwQ-32B.yaml` |
| [#5616](https://github.com/vllm-project/vllm-ascend/pull/5616) |
`test_qwen3_next_w8a8.py` | `Qwen3-Next-80B-A3B-Instruct-W8A8.yaml` |
| [#3541](https://github.com/vllm-project/vllm-ascend/pull/3541) |
`test_qwen2_5_vl_7b.py` | `Qwen2.5-VL-7B-Instruct.yaml` |
| [#5301](https://github.com/vllm-project/vllm-ascend/pull/5301) |
`test_qwen2_5_vl_7b_epd.py` | `Qwen2.5-VL-7B-Instruct-EPD.yaml` |
| [#3707](https://github.com/vllm-project/vllm-ascend/pull/3707) |
`test_qwen2_5_vl_32b.py` | `Qwen2.5-VL-32B-Instruct.yaml` |
| [#3676](https://github.com/vllm-project/vllm-ascend/pull/3676) |
`test_qwen3_32b_int8_a3_feature_stack3.py` |
`Qwen3-32B-Int8-A3-Feature-Stack3.yaml` |
| [#3709](https://github.com/vllm-project/vllm-ascend/pull/3709) |
`test_prefix_cache_qwen3_32b_int8.py` |
`Prefix-Cache-Qwen3-32B-Int8.yaml` |
| [#5395](https://github.com/vllm-project/vllm-ascend/pull/5395) |
`test_qwen3_next.py` | `Qwen3-Next-80B-A3B-Instruct-A2.yaml` |
| [#3474](https://github.com/vllm-project/vllm-ascend/pull/3474) |
`test_qwen3_32b.py` | `Qwen3-32B.yaml` |
| [#3541](https://github.com/vllm-project/vllm-ascend/pull/3541) |
`test_qwen3_32b_int8.py` | `Qwen3-32B-Int8-A2.yaml` |
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.15.0
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.15.0

---------

Signed-off-by: MrZ20 <2609716663@qq.com>
2026-03-03 20:13:43 +08:00

208 lines
7.9 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.
#
# This workflow related to the resources atlas 800 A3
# **Please note**: current A3 resource pool's maximum allowed concurrency is 5*16 NPUs
# We will limit the concurrency of jobs on A3 to avoid the risk of insufficient resources
name: Nightly-A3
on:
schedule:
# Run test at 24:00 Beijing time (UTC+8)
- cron: "0 16 * * *"
workflow_dispatch:
pull_request:
branches:
- 'main'
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}
concurrency:
group: ascend-nightly-${{ github.ref }}-a3
cancel-in-progress: true
jobs:
multi-node-tests:
name: multi-node
if: always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
strategy:
fail-fast: false
max-parallel: 1
matrix:
test_config:
- name: multi-node-deepseek-pd
config_file_path: DeepSeek-V3.yaml
size: 2
- name: multi-node-qwen3-dp
config_file_path: Qwen3-235B-A22B.yaml
size: 2
# - name: multi-node-dpsk-4node-pd
# config_file_path: DeepSeek-R1-W8A8.yaml
# size: 4
- name: multi-node-qwenw8a8-2node
config_file_path: Qwen3-235B-W8A8.yaml
size: 2
# - name: multi-node-deepseek-r1-w8a8-eplb
# config_file_path: DeepSeek-R1-W8A8-EPLB.yaml
# size: 4
- name: multi-node-qwenw8a8-2node-eplb
config_file_path: Qwen3-235B-W8A8-EPLB.yaml
size: 2
- name: multi-node-dpsk3.2-2node
config_file_path: DeepSeek-V3_2-W8A8-A3-dual-nodes.yaml
size: 2
- name: multi-node-qwen3-dp-mooncake-layerwise
config_file_path: Qwen3-235B-A22B-Mooncake-Layerwise.yaml
size: 2
- name: multi-node-deepseek-r1-w8a8-longseq
config_file_path: DeepSeek-R1-W8A8-longseq.yaml
size: 2
- name: multi-node-qwenw8a8-2node-longseq
config_file_path: Qwen3-235B-W8A8-longseq.yaml
size: 2
- name: multi-node-deepseek-V3_2-W8A8-cp
config_file_path: DeepSeek-V3_2-W8A8-cp.yaml
size: 2
- name: multi-node-qwen-disagg-pd
config_file_path: Qwen3-235B-disagg-pd.yaml
size: 2
- name: multi-node-qwen-vl-disagg-pd
config_file_path: Qwen3-VL-235B-disagg-pd.yaml
size: 2
- name: multi-node-kimi-k2-instruct-w8a8
config_file_path: Kimi-K2-Instruct-W8A8.yaml
size: 2
- name: multi-node-deepseek-v3.1
config_file_path: DeepSeek-V3.1-BF16.yaml
size: 2
uses: ./.github/workflows/_e2e_nightly_multi_node.yaml
with:
soc_version: a3
runner: linux-aarch64-a3-0
image: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:nightly-a3'
replicas: 1
size: ${{ matrix.test_config.size }}
config_file_path: ${{ matrix.test_config.config_file_path }}
secrets:
KUBECONFIG_B64: ${{ secrets.KUBECONFIG_B64 }}
single-node-tests:
name: single-node
if: always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
needs: [multi-node-tests]
strategy:
fail-fast: false
matrix:
test_config:
- name: qwen3-30b-acc
os: linux-aarch64-a3-4
tests: tests/e2e/weekly/single_node/models/test_qwen3_30b_acc.py
uses: ./.github/workflows/_e2e_nightly_single_node.yaml
with:
runner: ${{ matrix.test_config.os }}
image: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:nightly-a3'
tests: ${{ matrix.test_config.tests }}
name: ${{ matrix.test_config.name }}
single-node-yaml-tests:
name: single-node
if: always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
needs: [multi-node-tests]
strategy:
fail-fast: false
matrix:
test_config:
# YAML-driven tests
- name: deepseek-r1-0528-w8a8
os: linux-aarch64-a3-16
config_file_path: DeepSeek-R1-0528-W8A8.yaml
- name: deepseek-r1-w8a8-hbm
os: linux-aarch64-a3-16
config_file_path: DeepSeek-R1-W8A8-HBM.yaml
- name: deepseek-v3-2-w8a8
os: linux-aarch64-a3-16
config_file_path: DeepSeek-V3.2-W8A8.yaml
- name: kimi-k2-thinking
os: linux-aarch64-a3-16
config_file_path: Kimi-K2-Thinking.yaml
- name: mtpx-deepseek-r1-0528-w8a8
os: linux-aarch64-a3-16
config_file_path: MTPX-DeepSeek-R1-0528-W8A8.yaml
- name: qwen3-235b-a22b-w8a8
os: linux-aarch64-a3-16
config_file_path: Qwen3-235B-A22B-W8A8.yaml
- name: qwen3-30b-a3b-w8a8
os: linux-aarch64-a3-4
config_file_path: Qwen3-30B-A3B-W8A8.yaml
- name: qwen3-next-80b-a3b-instruct-w8a8
os: linux-aarch64-a3-4
config_file_path: Qwen3-Next-80B-A3B-Instruct-W8A8.yaml
- name: qwq-32b
os: linux-aarch64-a3-4
config_file_path: QwQ-32B.yaml
- name: qwen3-32b-int8
os: linux-aarch64-a3-4
config_file_path: Qwen3-32B-Int8.yaml
- name: qwen2-5-vl-7b
os: linux-aarch64-a3-4
config_file_path: Qwen2.5-VL-7B-Instruct.yaml
- name: qwen2-5-vl-7b-epd
os: linux-aarch64-a3-4
config_file_path: Qwen2.5-VL-7B-Instruct-EPD.yaml
- name: qwen2-5-vl-32b
os: linux-aarch64-a3-4
config_file_path: Qwen2.5-VL-32B-Instruct.yaml
- name: qwen3-32b-int8-a3-feature-stack3
os: linux-aarch64-a3-4
config_file_path: Qwen3-32B-Int8-A3-Feature-Stack3.yaml
- name: qwen3-32b-int8-prefix-cache
os: linux-aarch64-a3-4
config_file_path: Prefix-Cache-Qwen3-32B-Int8.yaml
- name: deepseek-r1-0528-w8a8-prefix-cache
os: linux-aarch64-a3-16
config_file_path: Prefix-Cache-DeepSeek-R1-0528-W8A8.yaml
uses: ./.github/workflows/_e2e_nightly_single_node.yaml
with:
runner: ${{ matrix.test_config.os }}
image: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:nightly-a3'
config_file_path: ${{ matrix.test_config.config_file_path }}
name: ${{ matrix.test_config.name }}
custom-ops-tests:
name: test ops
if: always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
needs: multi-node-tests
strategy:
fail-fast: false
matrix:
test_config:
- name: custom-multi-ops
os: linux-aarch64-a3-16
tests: tests/e2e/nightly/single_node/ops/multicard_ops_a3/
uses: ./.github/workflows/_e2e_nightly_single_node.yaml
with:
runner: ${{ matrix.test_config.os }}
image: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:nightly-a3'
tests: ${{ matrix.test_config.tests }}
name: ${{ matrix.test_config.name }}