Nan Jiang be804c1b83 [RL] Expose top-p-only sampling masks (#33593)

2026-08-14 16:40:27 -07:00

..

test_deterministic_gumbel_u1.py

Deterministic gumbel sampling: clamp u=1 so masked tokens can't be sampled (#33423)

2026-08-09 21:43:27 +08:00

test_original_logprobs.py

[CI] Rename basic CI stage-a/b/c -> base-a/b/c for symmetry with extra CI (#25420)

2026-05-15 18:26:55 -07:00

test_penalty.py

Bump FlashInfer to 0.6.17 and remove Kimi K3 workarounds (#33997)

2026-08-12 02:17:26 -07:00

test_pytorch_sampling_backend.py

[CI] Route mmlu and GB300 MMMU-Pro evals through sgl-eval (#34477)

2026-08-12 19:33:21 -07:00

test_sampling_mask.py

[RL] Expose top-p-only sampling masks (#33593)

2026-08-14 16:40:27 -07:00