iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[CI] Shard entrypoints API-server tests (#52344)

Browse Source 
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
This commit is contained in:
Kevin H. Luu
2026-09-02 01:13:38 -07:00
committed by GitHub
parent 62588e0592
commit 878ec4bfee
1 changed files with 6 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.buildkite/test_areas/entrypoints.yaml
+6 -5
View File
@@ -48,10 +48,11 @@ steps:
depends_on:
- image-build-amd
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (API Server)"
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (API Server) %N"
key: entrypoints-integration-api-server
device: h200_35gb
timeout_in_minutes: 75
parallelism: 4
working_dir: "/vllm-workspace/tests"
source_file_dependencies:
- vllm/
@@ -60,12 +61,12 @@ steps:
- tests/entrypoints/scale_out
commands:
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- pytest -v -s entrypoints/serve --ignore=entrypoints/serve/dev/rpc
- PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/serve/dev/rpc
- pytest -v -s entrypoints/scale_out
- pytest -v -s entrypoints/serve --ignore=entrypoints/serve/dev/rpc --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
- if [ "$$BUILDKITE_PARALLEL_JOB" = "1" ]; then PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/serve/dev/rpc; fi
- pytest -v -s entrypoints/scale_out --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB
mirror:
amd:
label: ":amd: (MI300) Entrypoints Integration (API Server)"
label: ":amd: (MI300) Entrypoints Integration (API Server) %N"
dind: false
device: mi300_1
timeout_in_minutes: 65