Skip to content

GitLab

Unverified Commit ca212880 authored by Lucas Wilkinson's avatar Lucas Wilkinson Committed by GitHub
Browse files

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


Signed-off-by: default avatarLucas Wilkinson <lwilkins@redhat.com>
parent 4c82b6fa
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 1 deletion
.buildkite/test-pipeline.yaml
View file @ ca212880
...@@ -1064,7 +1064,8 @@ steps: ...@@ -1064,7 +1064,8 @@ steps:
- tests/compile/test_fusion_attn.py - tests/compile/test_fusion_attn.py
commands: commands:
- export VLLM_TEST_CLEAN_GPU_MEMORY=1 - 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 - label: Hopper Fusion Distributed E2E Tests (2xH100) # 70min
timeout_in_minutes: 70 timeout_in_minutes: 70
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment