Skip to content

[TPU][V1][CI] Update regression test baseline for v6 CI #17064

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Apr 30, 2025
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 7 additions & 8 deletions tests/v1/tpu/test_perf.py
Original file line number Diff line number Diff line change
Expand Up @@ -59,17 +59,16 @@ class TestParams:
prefix_len=500,
decode_len=50,

# (This is the active CI/CD instance)
# commit id: ccb246776d93ef105904a8ec015b3587240a1183
# tpu: v5lite (vllm CI/CD)
expected_avg_time=1.4,
err_tol=0.30,
# tpu: v5lite (old vllm CI/CD)
# expected_avg_time=1.4,
# err_tol=0.30,

# (TODO: There is no v6e in CI/CD currently)
# (This is the active CI/CD instance)
# commit id: ccb246776d93ef105904a8ec015b3587240a1183
# tpu: v6e
# expected_avg_time=1.5,
# err_tol=0.20,
# tpu: v6e (current vllm CI/CD)
expected_avg_time=1.7, # measured with VLLM_XLA_CACHE_PATH=
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

any clue as to why the CI avg time would increase here with VLLM_XLA_CACHE_PATH=? @yaochengji
Testing locally on v6-4 this yields 1.35.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't have any clue. Previously I tested with VLLM_XLA_CACHE_PATH= and I didn't see any compilation time increase.

err_tol=0.20,
),
]

Expand Down