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

[CI] Fix attention benchmark smoke test (#45728)

Browse Source 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Matthew Bonanni
2026-06-16 13:43:37 +00:00
committed by GitHub
co-authored by Claude
parent ced32bb474
commit 040df8f2ea
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.buildkite/test-amd.yaml
+1 -1
View File
@@ -2759,7 +2759,7 @@ steps:
- vllm/_aiter_ops.py
- vllm/platforms/rocm.py
commands:
- python3 benchmarks/attention_benchmarks/benchmark.py --backends ROCM_ATTN ROCM_AITER_FA ROCM_AITER_UNIFIED_ATTN --batch-specs "8q1s1k" --repeats 1 --warmup-iters 1
- python3 benchmarks/attention_benchmarks/benchmark.py --backends ROCM_ATTN ROCM_AITER_FA ROCM_AITER_UNIFIED_ATTN --batch-specs "8q1s1k"
#-------------------------------------------------------- mi355 · distributed --------------------------------------------------------#
.buildkite/test_areas/benchmarks.yaml
+1 -1
View File
@@ -23,4 +23,4 @@ steps:
- benchmarks/attention_benchmarks/
- vllm/v1/attention/
commands:
- python3 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"