Adjust concurrency group for each npu workflow (#1068)
### What this PR does / why we need it? Adjust concurrency group for each npu workflow - for pd and benchmarks share the static-08-01, so only one job can runs on - other job one PR/schedule should have only 1 job runs ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? CI passed Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
This commit is contained in:
3
.github/workflows/accuracy_test.yaml
vendored
3
.github/workflows/accuracy_test.yaml
vendored
@@ -62,8 +62,9 @@ defaults:
|
|||||||
run:
|
run:
|
||||||
shell: bash -el {0}
|
shell: bash -el {0}
|
||||||
|
|
||||||
|
# only cancel in-progress runs of the same workflow
|
||||||
concurrency:
|
concurrency:
|
||||||
group: pr-${{ github.event.pull_request.number }}
|
group: ${{ github.workflow }}-${{ github.ref }}
|
||||||
cancel-in-progress: true
|
cancel-in-progress: true
|
||||||
|
|
||||||
jobs:
|
jobs:
|
||||||
|
|||||||
5
.github/workflows/nightly_benchmarks.yaml
vendored
5
.github/workflows/nightly_benchmarks.yaml
vendored
@@ -33,9 +33,10 @@ defaults:
|
|||||||
run:
|
run:
|
||||||
shell: bash -el {0}
|
shell: bash -el {0}
|
||||||
|
|
||||||
|
# only 1 job can runs on static-8-01-cards
|
||||||
concurrency:
|
concurrency:
|
||||||
group: pr-${{ github.event.pull_request.number }}
|
group: static-8-01-cards
|
||||||
cancel-in-progress: true
|
cancel-in-progress: false
|
||||||
|
|
||||||
jobs:
|
jobs:
|
||||||
test:
|
test:
|
||||||
|
|||||||
@@ -30,8 +30,9 @@ defaults:
|
|||||||
run:
|
run:
|
||||||
shell: bash -el {0}
|
shell: bash -el {0}
|
||||||
|
|
||||||
|
# only cancel in-progress runs of the same workflow
|
||||||
concurrency:
|
concurrency:
|
||||||
group: pr-${{ github.event.pull_request.number }}
|
group: ${{ github.workflow }}-${{ github.ref }}
|
||||||
cancel-in-progress: true
|
cancel-in-progress: true
|
||||||
|
|
||||||
jobs:
|
jobs:
|
||||||
@@ -43,15 +44,6 @@ jobs:
|
|||||||
matrix:
|
matrix:
|
||||||
os: [linux-arm64-npu-1, linux-arm64-npu-4]
|
os: [linux-arm64-npu-1, linux-arm64-npu-4]
|
||||||
vllm_version: [main, v0.9.0]
|
vllm_version: [main, v0.9.0]
|
||||||
concurrency:
|
|
||||||
group: >
|
|
||||||
${{
|
|
||||||
matrix.os == 'linux-arm64-npu-4'
|
|
||||||
&& github.event.pull_request.number
|
|
||||||
&& format('pr-{0}-limit-npu-4-long-term', github.event.pull_request.number)
|
|
||||||
|| format('job-{0}-{1}-{2}-long-term', matrix.os, matrix.vllm_version, github.event.pull_request.number)
|
|
||||||
}}
|
|
||||||
cancel-in-progress: false
|
|
||||||
name: vLLM Ascend long term test
|
name: vLLM Ascend long term test
|
||||||
runs-on: ${{ matrix.os }}
|
runs-on: ${{ matrix.os }}
|
||||||
container:
|
container:
|
||||||
|
|||||||
5
.github/workflows/vllm_ascend_test_pd.yaml
vendored
5
.github/workflows/vllm_ascend_test_pd.yaml
vendored
@@ -30,9 +30,10 @@ defaults:
|
|||||||
run:
|
run:
|
||||||
shell: bash -el {0}
|
shell: bash -el {0}
|
||||||
|
|
||||||
|
# only 1 job can runs on static-8-01-cards
|
||||||
concurrency:
|
concurrency:
|
||||||
group: pr-${{ github.event.pull_request.number }}
|
group: static-8-01-cards
|
||||||
cancel-in-progress: true
|
cancel-in-progress: false
|
||||||
|
|
||||||
jobs:
|
jobs:
|
||||||
prefilling-decoding-disaggregation:
|
prefilling-decoding-disaggregation:
|
||||||
|
|||||||
Reference in New Issue
Block a user