Skip to content

Commit 18c31f8

Browse files
zzzzwwjjzzzzwwjj
authored
Merge branch 'main' into ascend_forward_context_refactor
2 parents a62eb0e + e3a2443 commit 18c31f8

File tree

90 files changed

+4587
-1224
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

90 files changed

+4587
-1224
lines changed

‎.github/PULL_REQUEST_TEMPLATE.md‎

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -25,4 +25,3 @@ CI passed with new added/existing test.
2525
If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future.
2626
If tests were not added, please describe why they were not added and/or why it was difficult to add.
2727
-->
28-

‎.github/workflows/accuracy_test.yaml‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@ on:
3737
# Current supported vLLM versions
3838
options:
3939
- main
40-
- v0.9.2
40+
- v0.10.0
4141
- v0.9.1
4242
- v0.7.3
4343
vllm-ascend-version:
@@ -123,7 +123,7 @@ jobs:
123123
fail-fast: false
124124
name: ${{ matrix.model_name }} accuracy
125125
container:
126-
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.1.rc1-910b-ubuntu22.04-py3.10
126+
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
127127
env:
128128
DATASET_SOURCE: ModelScope
129129
VLLM_USE_MODELSCOPE: True
@@ -163,7 +163,7 @@ jobs:
163163
repository: vllm-project/vllm
164164
path: ./vllm-empty
165165
# Please also update this when bump matched version
166-
ref: ${{ github.event.inputs.vllm-version || 'v0.9.2' }}
166+
ref: ${{ github.event.inputs.vllm-version || 'v0.10.0' }}
167167

168168
- name: Install vllm-project/vllm from source
169169
working-directory: ./vllm-empty

‎.github/workflows/nightly_benchmarks.yaml‎

Lines changed: 2 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -51,12 +51,12 @@ jobs:
5151
strategy:
5252
matrix:
5353
include:
54-
- vllm_branch: v0.9.2
54+
- vllm_branch: v0.10.0
5555
vllm_ascend_branch: main
5656
vllm_use_v1: 1
5757
max-parallel: 1
5858
container:
59-
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.1.rc1-910b-ubuntu22.04-py3.10
59+
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
6060
volumes:
6161
- /usr/local/dcmi:/usr/local/dcmi
6262
- /usr/local/bin/npu-smi:/usr/local/bin/npu-smi
@@ -117,7 +117,6 @@ jobs:
117117
env:
118118
PIP_EXTRA_INDEX_URL: https://mirrors.huaweicloud.com/ascend/repos/pypi
119119
run: |
120-
pip install "transformers<=4.52.4"
121120
pip install -e .
122121
pip install -r benchmarks/requirements-bench.txt
123122

‎.github/workflows/vllm_ascend_test.yaml‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -75,13 +75,13 @@ jobs:
7575
if: ${{ needs.lint.result == 'success' && (needs.changes.outputs.e2e_tracker == 'true' || needs.changes.outputs.ut_tracker == 'true') }}
7676
runs-on: ubuntu-latest
7777
container:
78-
image: quay.io/ascend/cann:8.1.rc1-910b-ubuntu22.04-py3.10
78+
image: quay.io/ascend/cann:8.2.rc1-910b-ubuntu22.04-py3.11
7979
env:
8080
VLLM_LOGGING_LEVEL: ERROR
8181
VLLM_USE_MODELSCOPE: True
8282
strategy:
8383
matrix:
84-
vllm_version: [main, v0.9.2]
84+
vllm_version: [main, v0.10.0]
8585
steps:
8686
- name: Install packages
8787
run: |
@@ -137,11 +137,11 @@ jobs:
137137
max-parallel: 2
138138
matrix:
139139
os: [linux-arm64-npu-1]
140-
vllm_version: [main, v0.9.2]
140+
vllm_version: [main, v0.10.0]
141141
name: singlecard e2e test
142142
runs-on: ${{ matrix.os }}
143143
container:
144-
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.1.rc1-910b-ubuntu22.04-py3.10
144+
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
145145
env:
146146
VLLM_LOGGING_LEVEL: ERROR
147147
VLLM_USE_MODELSCOPE: True
@@ -216,11 +216,11 @@ jobs:
216216
max-parallel: 1
217217
matrix:
218218
os: [linux-arm64-npu-4]
219-
vllm_version: [main, v0.9.2]
219+
vllm_version: [main, v0.10.0]
220220
name: multicard e2e test
221221
runs-on: ${{ matrix.os }}
222222
container:
223-
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.1.rc1-910b-ubuntu22.04-py3.10
223+
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
224224
env:
225225
VLLM_LOGGING_LEVEL: ERROR
226226
VLLM_USE_MODELSCOPE: True

‎.github/workflows/vllm_ascend_test_long_term.yaml‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -43,11 +43,11 @@ jobs:
4343
max-parallel: 2
4444
matrix:
4545
os: [linux-arm64-npu-1, linux-arm64-npu-4]
46-
vllm_version: [main, v0.9.2]
46+
vllm_version: [main, v0.10.0]
4747
name: vLLM Ascend long term test
4848
runs-on: ${{ matrix.os }}
4949
container:
50-
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.1.rc1-910b-ubuntu22.04-py3.10
50+
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
5151
env:
5252
VLLM_LOGGING_LEVEL: ERROR
5353
VLLM_USE_MODELSCOPE: True

‎.github/workflows/vllm_ascend_test_pd.yaml‎

Lines changed: 4 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -42,15 +42,14 @@ jobs:
4242
strategy:
4343
matrix:
4444
vllm_verison: [
45-
# revert me when V1 disaggregation prefill is merged in main
46-
# main,
45+
main,
4746
v0.9.1
4847
]
4948
name: vLLM Ascend prefilling decoding disaggregation test
5049
runs-on: linux-arm64-npu-static-8
5150

5251
container:
53-
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.1.rc1-910b-ubuntu22.04-py3.10
52+
image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.2.rc1-910b-ubuntu22.04-py3.11
5453
volumes:
5554
- /usr/local/dcmi:/usr/local/dcmi
5655
- /usr/local/bin/npu-smi:/usr/local/bin/npu-smi
@@ -107,6 +106,6 @@ jobs:
107106
pip install -r requirements-dev.txt
108107
pip install -v -e .
109108
110-
- name: Run vllm-project/vllm-ascend PD Disaggregation test
109+
- name: Run vllm-project/vllm-ascend PD Disaggregation edge test
111110
run: |
112-
pytest -sv tests/e2e/pd_disaggreate/test_pd_e2e.py
111+
bash tests/e2e/pd_disaggreate/run_edge_case_test.sh

‎.pre-commit-config.yaml‎

Lines changed: 11 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -46,11 +46,11 @@ repos:
4646
# files: ^csrc/.*\.(cpp|hpp|cc|hh|cxx|hxx)$
4747
# types_or: [c++]
4848
# args: [--style=google, --verbose]
49-
# - repo: https://github.com/jackdewinter/pymarkdown
50-
# rev: v0.9.29
51-
# hooks:
52-
# - id: pymarkdown
53-
# args: [fix]
49+
- repo: https://github.com/jackdewinter/pymarkdown
50+
rev: v0.9.29
51+
hooks:
52+
- id: pymarkdown
53+
args: [fix]
5454
- repo: https://github.com/rhysd/actionlint
5555
rev: v1.7.7
5656
hooks:
@@ -131,6 +131,12 @@ repos:
131131
types: [python]
132132
pass_filenames: false
133133
additional_dependencies: [regex]
134+
- id: python-init
135+
name: Enforce __init__.py in Python packages
136+
entry: python tools/check_python_src_init.py
137+
language: python
138+
types: [python]
139+
pass_filenames: false
134140
# Keep `suggestion` last
135141
- id: suggestion
136142
name: Suggestion

‎CODE_OF_CONDUCT.md‎

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -125,4 +125,3 @@ Community Impact Guidelines were inspired by
125125
For answers to common questions about this code of conduct, see the
126126
[Contributor Covenant FAQ](https://www.contributor-covenant.org/faq). Translations are available at
127127
[Contributor Covenant translations](https://www.contributor-covenant.org/translations).
128-

‎Dockerfile‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@
1515
# This file is a part of the vllm-ascend project.
1616
#
1717

18-
FROM quay.io/ascend/cann:8.1.rc1-910b-ubuntu22.04-py3.10
18+
FROM quay.io/ascend/cann:8.2.rc1-910b-ubuntu22.04-py3.11
1919

2020
ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
2121
ARG COMPILE_CUSTOM_KERNELS=1
@@ -37,7 +37,7 @@ RUN pip config set global.index-url ${PIP_INDEX_URL}
3737

3838
# Install vLLM
3939
ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
40-
ARG VLLM_TAG=v0.9.2
40+
ARG VLLM_TAG=v0.10.0
4141
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
4242
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
4343
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \

‎Dockerfile.310p‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@
1515
# This file is a part of the vllm-ascend project.
1616
#
1717

18-
FROM quay.io/ascend/cann:8.1.rc1-310p-ubuntu22.04-py3.10
18+
FROM quay.io/ascend/cann:8.2.rc1-310p-ubuntu22.04-py3.11
1919

2020
ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
2121
ARG COMPILE_CUSTOM_KERNELS=1
@@ -37,7 +37,7 @@ RUN pip config set global.index-url ${PIP_INDEX_URL}
3737

3838
# Install vLLM
3939
ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
40-
ARG VLLM_TAG=v0.9.2
40+
ARG VLLM_TAG=v0.10.0
4141
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
4242
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
4343
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \

0 commit comments

Comments
 (0)