Skip to content

Commit 5897dc5

Browse files
authored
[Build] Bump vLLM version to v0.8.5.post1 (#755)
### What this PR does / why we need it? Bump vllm version to v0.8.5.post1 ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? CI passed Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
1 parent d6bfae8 commit 5897dc5

File tree

3 files changed

+4
-4
lines changed

3 files changed

+4
-4
lines changed

.github/workflows/vllm_ascend_test.yaml

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -48,7 +48,7 @@ jobs:
4848
max-parallel: 2
4949
matrix:
5050
os: [linux-arm64-npu-1, linux-arm64-npu-4]
51-
vllm_verison: [main, v0.8.5]
51+
vllm_verison: [main, v0.8.5.post1]
5252
concurrency:
5353
group: >
5454
${{
@@ -153,7 +153,7 @@ jobs:
153153
154154
- name: Run vllm-project/vllm-ascend Speculative Decode test
155155
# speculative decode seems will cause oom issue, only disable it now on ci test with vLLM main
156-
if: matrix.vllm_verison == 'v0.8.5' && steps.filter_spec_decode.outputs.speculative_tests_changed == 'true' || github.event_name == 'schedule'
156+
if: matrix.vllm_verison == 'v0.8.5.post1' && steps.filter_spec_decode.outputs.speculative_tests_changed == 'true' || github.event_name == 'schedule'
157157
run: |
158158
if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then
159159
pytest -sv tests/singlecard/spec_decode/e2e/test_mtp_correctness.py # it needs a clean process

Dockerfile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -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=v0.8.5
40+
ARG VLLM_TAG=v0.8.5.post1
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.openEuler

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -34,7 +34,7 @@ COPY . /vllm-workspace/vllm-ascend/
3434

3535
# Install vLLM
3636
ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
37-
ARG VLLM_TAG=v0.8.5
37+
ARG VLLM_TAG=v0.8.5.post1
3838

3939
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
4040
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.

0 commit comments

Comments
 (0)