[CI] Fix OOM in Hopper Fusion E2E Tests (H100) (#32489)

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

[CI] Fix OOM in Hopper Fusion E2E Tests (H100) (#32489)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
ca212880 · Lucas Wilkinson · GitHub · 4c82b6fa · ca212880
Unverified Commit ca212880 authored Jan 16, 2026 by Lucas Wilkinson Committed by GitHub Jan 16, 2026
Show whitespace changes
Inline Side-by-side

Showing with 2 additions and 1 deletion

.buildkite/test-pipeline.yaml .buildkite/test-pipeline.yaml +2 -1

No files found.
--- a/.buildkite/test-pipeline.yaml
+++ b/.buildkite/test-pipeline.yaml
@@ -1064,7 +1064,8 @@ steps:
  - tests/compile/test_fusion_attn.py
  commands:
    - export VLLM_TEST_CLEAN_GPU_MEMORY=1
-    - pytest -v -s tests/compile/test_fusion_attn.py
+    # skip Llama-4 since it does not fit on this device
+    - pytest -v -s tests/compile/test_fusion_attn.py -k 'not Llama-4'

 - label: Hopper Fusion Distributed E2E Tests (2xH100)  # 70min
  timeout_in_minutes: 70