Issue Station
Sign In
Tools hereToolbox

vllm - 💡(How to fix) Fix [CI Failure]: GPQA Eval (GPT-OSS) (B200) - gpt-oss-20b-flashinfer-mxfp4-mxfp8-cutlass [1 pull requests]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Root Cause

  • Flaky test
  • Can reproduce locally
  • Caused by external libraries (e.g. bug in transformers)

Fix Action

Fixed

RAW_BUFFERClick to expand / collapse

Name of failing test

evals/gpt_oss/test_gpqa_correctness.py::test_gpqa_correctness[gpt-oss-20b-flashinfer-mxfp4-mxfp8-cutlass]

Basic information

  • Flaky test
  • Can reproduce locally
  • Caused by external libraries (e.g. bug in transformers)

🧪 Describe the failing test

Currently the test just "hangs" forever due to the model producing gibberish until it times out

📝 History of failing test

I believe it is because due to https://github.com/vllm-project/vllm/pull/40960 hardcoding is_sf_swizzled_layout=False in the mxfp8 branch of moe_kernel_quantize_input

CC List.

No response

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#SSR setup#ISR setup#authentication setup#request error#file not found

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING