[CI][torch.compile] Reduce e2e fusion test time (#33293)

Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: ProExpertProg <luka.govedic@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
This commit is contained in:
Luka Govedič
2026-02-04 19:09:03 -05:00
committed by GitHub
parent 439afa4eea
commit 4d9513537d
17 changed files with 1068 additions and 821 deletions

View File

@@ -18,7 +18,7 @@ steps:
- "find compile/ -maxdepth 1 -name 'test_*.py' -print0 | xargs -0 -n1 -I{} pytest -s -v '{}'"
- label: PyTorch Fullgraph Smoke Test
timeout_in_minutes: 30
timeout_in_minutes: 35
source_file_dependencies:
- vllm/
- tests/compile
@@ -30,16 +30,13 @@ steps:
- "find compile/fullgraph/ -name 'test_*.py' -not -name 'test_full_graph.py' -exec pytest -s -v {} \\;"
- label: PyTorch Fullgraph
timeout_in_minutes: 40
timeout_in_minutes: 30
source_file_dependencies:
- vllm/
- tests/compile
commands:
# fp8 kv scales not supported on sm89, tested on Blackwell instead
- pytest -v -s compile/fullgraph/test_full_graph.py -k 'not test_fp8_kv_scale_compile'
# Limit to no custom ops to reduce running time
# Wrap with quotes to escape yaml and avoid starting -k string with a -
- "pytest -v -s compile/distributed/test_fusions_e2e.py -k 'TRITON and not +quant_fp8 and not Llama-4'"
- label: Pytorch Nightly Dependency Override Check # 2min
# if this test fails, it means the nightly torch version is not compatible with some