Nick Hill ec8d60bea8 [Model Runner V2] Use FlashInfer sampler (#42472)

2026-06-03 07:59:31 -07:00

..

__init__.py

[Model Runner V2] Add sample/ directory and reorganize files (#29719)

2025-11-29 00:41:01 -08:00

bad_words.py

[ModelRunnerV2] Rename sampler functions and variables for clarity (#35459)

2026-03-02 19:48:56 -08:00

gumbel.py

[Model Runner V2] FP32 gumbel sampling. (#41775)

2026-05-15 09:20:08 -07:00

logit_bias.py

[ModelRunnerV2] Rename sampler functions and variables for clarity (#35459)

2026-03-02 19:48:56 -08:00

logprob.py

[Model Runner V2] Bug fix: logprob dtype int64/int32 issue (#41761)

2026-05-11 21:55:43 +00:00

min_p.py

[ModelRunnerV2] Rename sampler functions and variables for clarity (#35459)

2026-03-02 19:48:56 -08:00

output.py

[Model Runner V2] Add probabilistic rejection sampling for spec decoding (#35461)

2026-03-11 14:04:32 -07:00

penalties.py

[Bugfix][Performance Improvement] Improve penalties triton kernel performance (#40657)

2026-05-12 05:47:20 +00:00

prompt_logprob.py

[ModelRunnerV2] Avoid pipeline parallel bubbles (#42187)

2026-06-02 14:02:01 -07:00

sampler.py

[Model Runner V2] Use FlashInfer sampler (#42472)

2026-06-03 07:59:31 -07:00

states.py

[Model Runner V2] Use FlashInfer sampler (#42472)

2026-06-03 07:59:31 -07:00