yihengandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 652d962bc9 [Model Runner V2][Spec Decode] Reduce TP communication for draft token generation (#46448) ...

Signed-off-by: EanWang211123 <wangyiheng@sangfor.com.cn>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-06-25 19:30:07 -07:00

..

autoregressive

[MRV2][Spec Decode] DFlash (#44586)

2026-06-10 08:47:46 -07:00

dflash

[Model Runner V2][DFlash] Enable dflash attention backend selection (#46770)

2026-06-25 19:29:25 -07:00

eagle

[CI/Build][Bugfix] Fix SD LoRA (#45941)

2026-06-18 00:34:15 +00:00

gemma4

[Model Runner V2][Spec Decode] Add Gemma4 MTP support (#43241)

2026-06-04 00:51:06 +00:00

mtp

[Model Runner V2][Spec Decode] Add Gemma4 MTP support (#43241)

2026-06-04 00:51:06 +00:00

__init__.py

[MRV2][Spec Decode] DFlash (#44586)

2026-06-10 08:47:46 -07:00

rejection_sampler_utils.py

[Model Runner V2][Spec Decode] Use log1p to compute residual during rejection sampling (#46665)

2026-06-25 23:46:10 +00:00

rejection_sampler.py

[Model] Add DiffusionGemma Support (#45163)

2026-06-11 22:17:35 -07:00

speculator.py

[Model Runner V2][Spec Decode] Reduce TP communication for draft token generation (#46448)

2026-06-25 19:30:07 -07:00

utils.py

[Model] Add DiffusionGemma Support (#45163)

2026-06-11 22:17:35 -07:00