[Bug] test_dflash_qwen3_5_4b flaky-marginal in DGX_H100-PyTorch-5: mean accepted 0.9909 < 1.0, alternating [True]/[False] variants

[chang-l]

Summary

unittest/_torch/speculative/hw_agnostic/test_dflash.py::test_dflash_qwen3_5_4b fails whenever the pre-merge stage DGX_H100-PyTorch-5 runs, with:

AssertionError: mean avg accepted 0.99 < threshold 1.0 (per request: ['1.37', '0.57', '1.03'])
assert 0.9908895492553711 >= 1.0

Identical numeric outcome (0.9908895) across independent runs, but the failing parametrization alternates: on L0_MergeRequest_PR build 47135 [False] failed while [True] passed; on build 47357 [True] failed while [False] passed (both on PR #15730, an unrelated VisualGen test PR, base = current main). Looks like whichever variant runs in a particular session position/state lands at 0.9909 against the exact-1.0 threshold.

Impact

Pre-merge blocker for unrelated PRs whose runs select the stage; the threshold of exactly 1.0 leaves zero margin.

Ask

Relax the threshold / deflake, or waive both variants until fixed. Related platform-level waives already exist for TestQwen3_5_4B::test_dflash (nvbug 6273850).