3 people 0f8b398158 [watermarking] add context deduplication support to speculative decoding (#56807) ...

Signed-off-by: Raphael Rialland <raphael.rialland@mistral.ai>
Signed-off-by: Simon Veitner <sveitner@redhat.com>
Co-authored-by: Simon Veitner <sveitner@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>

2026-09-30 12:22:10 -04:00

..

logits_processor

[MRV2] Validate MRV2 entrypoint logits processors (#57728)

2026-09-24 09:07:26 +00:00

__init__.py

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

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

bad_words.py

[Model Runner V2] Support custom logits processors (#56497)

2026-09-19 17:46:49 +00:00

batch_shard.py

[AuxOutput] Add block-keyed storage for routed-expert outputs (#45635)

2026-09-21 10:25:05 +00:00

gumbel.py

[watermarking] add context deduplication support to speculative decoding (#56807)

2026-09-30 12:22:10 -04:00

logit_bias.py

[Model Runner V2] Support custom logits processors (#56497)

2026-09-19 17:46:49 +00:00

logprob.py

[Feature] Add fixed-token prefill scoring (#54335)

2026-09-28 07:50:09 -07:00

min_p.py

[Bugfix][Model Runner V2][Spec Decode] Fix int32 offset overflow in sampler kernels (#46560)

2026-06-24 11:00:57 -07:00

output.py

[AuxOutput] Add block-keyed storage for routed-expert outputs (#45635)

2026-09-21 10:25:05 +00:00

penalties.py

[Model Runner V2] Support custom logits processors (#56497)

2026-09-19 17:46:49 +00:00

prompt_logprob.py

[Feature] Add fixed-token prefill scoring (#54335)

2026-09-28 07:50:09 -07:00

sampler.py

[MRV2][XPU] use xpu sample kernel in mrv2 sampler (#57277)

2026-09-21 13:24:41 +08:00

states.py

[Model Runner V2] Support custom logits processors (#56497)

2026-09-19 17:46:49 +00:00

thinking_budget.py

[Model Runner V2] Support custom logits processors (#56497)

2026-09-19 17:46:49 +00:00

trace_replay.py

[Core][V1] Support trace_decode_token_ids for deterministic decode replay (#46701)

2026-08-20 15:12:43 +08:00

watermark.py

[watermarking] add context deduplication support to speculative decoding (#56807)

2026-09-30 12:22:10 -04:00