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

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2026-01-16 14:27:16 -07:00
parent 4c82b6fac7
commit ca21288080
1 changed files with 2 additions and 1 deletions
--- 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