zhrrr 8f121f7879 [Model Runner V2] support auto resolve cudagraph mode/sizes based on attn backend (#32936) ...

Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>

2026-04-10 08:27:15 -07:00

..

eagle

[Model Runner V2] support auto resolve cudagraph mode/sizes based on attn backend (#32936)

2026-04-10 08:27:15 -07:00

__init__.py

[Model Runner V2] Support Eagle3 (no CUDA graph) (#35029)

2026-02-21 12:55:24 -08:00

probabilistic_rejection_sampler_utils.py

[Model Runner V2] Fuse probabilistic rejection sample kernels (#38496)

2026-04-07 17:37:37 -07:00

rejection_sampler.py

[Model Runner V2] Fuse probabilistic rejection sample kernels (#38496)

2026-04-07 17:37:37 -07:00

synthetic_rejection_sampler_utils.py

[Model Runner V2] Enable forcing a specific acceptance rate during rejection sampling (#38045)

2026-03-26 13:38:12 -07:00

utils.py

[Core] Don't schedule spec tokens with prefill chunks (#33652)

2026-02-04 23:40:22 +00:00