Alison ShaoandAlison Shao 7b44bc923e Relax flaky B200 GSM8K accuracy thresholds (#20304) ...

Co-authored-by: Alison Shao <alisonshao@Mac.attlocal.net>

2026-03-11 12:35:21 -07:00

..

test_deepseek_v3_fp4_mtp_small.py

[Spec] Refactor NaN/OOB checks to async maybe_detect_* with env-var control (#19899)

2026-03-05 13:51:05 -08:00

test_eagle3_basic.py

[AMD] Fix EAGLE3 speculative decoding with aiter attention backend (#19362)

2026-03-03 16:12:13 -08:00

test_eagle_constrained_decoding.py

[Spec] Refactor NaN/OOB checks to async maybe_detect_* with env-var control (#19899)

2026-03-05 13:51:05 -08:00

test_eagle_dp_attention.py

[Spec] Refactor NaN/OOB checks to async maybe_detect_* with env-var control (#19899)

2026-03-05 13:51:05 -08:00

test_eagle_infer_a.py

…

test_eagle_infer_b.py

[CI] Relax Eagle infer_b spec accept length threshold (#20300)

2026-03-10 15:40:52 -07:00

test_eagle_infer_beta_dp_attention_large.py

[Spec] Refactor NaN/OOB checks to async maybe_detect_* with env-var control (#19899)

2026-03-05 13:51:05 -08:00

test_eagle_infer_beta_dp_attention.py

Relax flaky B200 GSM8K accuracy thresholds (#20304)

2026-03-11 12:35:21 -07:00

test_eagle_infer_beta.py

Support return_logprob for spec v2 (overlap safe) (#19801)

2026-03-10 15:38:27 -07:00