bc69d7cfe1
Bump vLLM version to v0.11.2 What's broken and changed by vLLM: 1. structured_output is broken by https://github.com/vllm-project/vllm/pull/26866 2. get_mrope_input_positions is broken by https://github.com/vllm-project/vllm/pull/28399 3. graph mode is broken by https://github.com/vllm-project/vllm/pull/25110 we'll upgrade torch to 2.8 to fix the problem later 4. embedding is broken by https://github.com/vllm-project/vllm/pull/27583 5. `get_attn_backend_cls` and attention backend is broken are broken by https://github.com/vllm-project/vllm/pull/28534 6. spec decode is broken by https://github.com/vllm-project/vllm/pull/28771 7. sp feature is broken by https://github.com/vllm-project/vllm/pull/27126 8. mtp is broken by https://github.com/vllm-project/vllm/pull/27922 9. lora is broken by https://github.com/vllm-project/vllm/pull/21068 10. execute_model is broken by https://github.com/vllm-project/vllm/pull/26866 11. `VLLM_DISABLE_SHARED_EXPERTS_STREAM` env is broken by https://github.com/vllm-project/vllm/pull/28159 12. kv cahe is broken by https://github.com/vllm-project/vllm/pull/27753 13. dp is broken by https://github.com/vllm-project/vllm/pull/25110 What's broken and changed by ourself: 1. qwen vl is broken by https://github.com/vllm-project/vllm/pull/28455 We'll remove model files in the future to avoid this kind of error 2. Engine core is broken by https://github.com/vllm-project/vllm/pull/23691 We'll remove the patch file in the future. 3. Ascend scheduler is broken by https://github.com/vllm-project/vllm/pull/28733 We'll remove ascend scheudler later. 4. qwen3-next is broken by https://github.com/vllm-project/vllm/pull/28083 We'll remove model files in the future to avoid this kind of error 5. qwen vl is broken by https://github.com/vllm-project/vllm/pull/27764. We'll remove model files in the future Known issue: 1. ray doesn't work 2. the accuracy of qwen3-next is not correct 3. qwen3-vl is broken 4. prefix cache+ ascend scheduler + deepseek v2 lite is broken. Co-authored-by: MengqingCao <cmq0113@163.com> Co-authored-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: leo-pony <nengjunma@outlook.com> Co-authored-by: 22dimensions <waitingwind@foxmail.com> Co-authored-by: shen-shanshan <467638484@qq.com> - vLLM version: v0.11.2 --------- Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: MengqingCao <cmq0113@163.com> Signed-off-by: hfadzxy <starmoon_zhang@163.com> Signed-off-by: leo-pony <nengjunma@outlook.com> Co-authored-by: MengqingCao <cmq0113@163.com> Co-authored-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: leo-pony <nengjunma@outlook.com>
144 lines
5.5 KiB
YAML
144 lines
5.5 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: 'ascend test / nightly-a3'
|
|
|
|
on:
|
|
schedule:
|
|
# Run test at 24:00 Beijing time (UTC+8)
|
|
- cron: "0 16 * * *"
|
|
workflow_dispatch:
|
|
pull_request:
|
|
branches:
|
|
- 'main'
|
|
|
|
# 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-A3B.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-glm-2node
|
|
config_file_path: GLM-4_5.yaml
|
|
size: 2
|
|
- name: multi-node-dpsk3.2-exp-2node
|
|
config_file_path: DeepSeek-V3_2-Exp-bf16.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
|
|
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: qwen3-32b-in8-a3
|
|
os: linux-aarch64-a3-4
|
|
tests: tests/e2e/nightly/models/test_qwen3_32b_int8.py
|
|
- name: qwen3-32b-int8-a3-feature-stack3
|
|
os: linux-aarch64-a3-4
|
|
tests: tests/e2e/nightly/features/test_qwen3_32b_int8_a3_feature_stack3.py
|
|
- name: qwen3-235b-a22b-w8a8-eplb
|
|
os: linux-aarch64-a3-16
|
|
tests: tests/e2e/nightly/models/test_qwen3_235b_a22b_w8a8_eplb.py
|
|
- name: deepseek-r1-w8a8-eplb
|
|
os: linux-aarch64-a3-16
|
|
tests: tests/e2e/nightly/models/test_deepseek_r1_w8a8_eplb.py
|
|
- name: deepseek-r1-w8a8-mtpx
|
|
os: linux-aarch64-a3-16
|
|
tests: tests/e2e/nightly/features/test_mtpx_deepseek_r1_0528_w8a8.py
|
|
- name: qwen2-5-vl-7b
|
|
os: linux-aarch64-a3-4
|
|
tests: tests/e2e/nightly/models/test_qwen2_5_vl_7b.py
|
|
- name: qwen2-5-vl-32b
|
|
os: linux-aarch64-a3-4
|
|
tests: tests/e2e/nightly/models/test_qwen2_5_vl_32b.py
|
|
- name: qwen3-32b-int8-prefix-cache
|
|
os: linux-aarch64-a3-4
|
|
tests: tests/e2e/nightly/features/test_prefix_cache_qwen3_32b_int8.py
|
|
- name: deepseek-r1-0528-w8a8
|
|
os: linux-aarch64-a3-16
|
|
tests: tests/e2e/nightly/models/test_deepseek_r1_0528_w8a8.py
|
|
- name: deepseek-r1-0528-w8a8-prefix-cache
|
|
os: linux-aarch64-a3-16
|
|
tests: tests/e2e/nightly/features/test_prefix_cache_deepseek_r1_0528_w8a8.py
|
|
- name: qwq-32b-a3
|
|
os: linux-aarch64-a3-4
|
|
tests: tests/e2e/nightly/models/test_qwq_32b.py
|
|
- name: qwen3-30b-w8a8
|
|
os: linux-aarch64-a3-2
|
|
tests: tests/e2e/nightly/models/test_qwen3_30b_w8a8.py
|
|
- name: qwen3-235b-w8a8
|
|
os: linux-aarch64-a3-16
|
|
tests: tests/e2e/nightly/models/test_qwen3_235b_w8a8.py
|
|
- name: deepseek3_2-exp-w8a8
|
|
os: linux-aarch64-a3-16
|
|
tests: tests/e2e/nightly/models/test_deepseek_v3_2_exp_w8a8.py
|
|
uses: ./.github/workflows/_e2e_nightly_single_node.yaml
|
|
with:
|
|
vllm: v0.11.2
|
|
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 }}
|