EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[CI]Add performance CI for VLM (#6038)

Browse Source 
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
This commit is contained in:
XinyuanTong
2025-05-07 19:20:03 -07:00
committed by GitHub
parent 73600673bb
commit e88dd482ed
5 changed files with 219 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
.github/workflows/pr-test.yml vendored
View File

@@ -162,6 +162,18 @@ jobs:
cd test/srt
python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default_fp8
- name: Benchmark VLM offline throughput
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_bench_serving.TestBenchServing.test_vlm_offline_throughput
- name: Benchmark VLM online latency
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_bench_serving.TestBenchServing.test_vlm_online_latency
performance-test-2-gpu:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
github.event.pull_request.draft == false