3 people 7b544ecb52 [Spec Decode][Perf] Fuse the MTP trailing all-reduce; local-argmax draft tokens (#49793) ...

Signed-off-by: Peiyuan Zhou <peiyuanzhou1994@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-08-14 17:07:07 -07:00

..

common

[DSV4] Implement Sequence Parallelism (#46789)

2026-08-01 10:22:33 -07:00

deepseek_v4

[5/N][KV-Cache Layout Refactor] Backend-published KV packing via customize_spec (#51704)

2026-08-14 09:47:55 -04:00

deepseek_v32

[Spec Decode][Perf] Fuse the MTP trailing all-reduce; local-argmax draft tokens (#49793)

2026-08-14 17:07:07 -07:00

dots3_note

[Bugfix] Disable sequence parallelism for Dots3 NOTE (#52172)

2026-08-13 22:13:00 +08:00

inkling

[Bugfix] Support HF-config compat for Inkling (#51850)

2026-08-11 15:32:28 -04:00

kimi_k3

[Model][Spec Decode] Tap the pre-norm AttnRes mixture as the Kimi K3 DFlash aux state (#50487)

2026-08-14 09:03:42 -07:00

minimax_m3

[Misc] Remove deprecated calculate_kv_scales runtime KV scale calculation (#49389)

2026-08-03 11:15:13 -04:00

__init__.py

[Model Refactoring] Migrate DeepSeek V4 to vllm/models/ [1/N] (#43004)

2026-05-18 19:50:02 -07:00