biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Benchmarks] Fix attention benchmark smoke test (#34269)

Browse Source 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Matthew Bonanni
2026-02-10 16:04:07 -05:00
committed by GitHub
parent 506ad7d7c1
commit 4293c00b84
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.buildkite/test_areas/benchmarks.yaml
View File

@@ -22,9 +22,10 @@ steps:
device: b200
num_gpus: 2
optional: true
working_dir: "/vllm-workspace/"
timeout_in_minutes: 10
source_file_dependencies:
- benchmarks/attention_benchmarks/
- vllm/v1/attention/
commands:
- python benchmarks/attention_benchmarks/benchmark.py --backends flash flashinfer --batch-specs "8q1s1k" --repeats 1 --warmup-iters 1
- python3 benchmarks/attention_benchmarks/benchmark.py --backends flash flashinfer --batch-specs "8q1s1k" --repeats 1 --warmup-iters 1