vLLM/vllm/models at edd4c8176cfd98ece8a29beda574378c42971967 - vLLM

iHore/vLLM

Fork 0

Files

T

History

edd4c8176c [Bugfix][DSv4] Revert adaptive C128A metadata packing (#51318 )

Signed-off-by: tobymao <toby.mao@gmail.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>

2026-08-15 18:39:23 -07:00

common

[DSV4] Implement Sequence Parallelism (#46789 )

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

deepseek_v4

[Bugfix][DSv4] Revert adaptive C128A metadata packing (#51318 )

2026-08-15 18:39:23 -07:00

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 )