vLLM/vllm/models at 811d12ee26fa119cf8faae44d80330becf1e7fe3 - vLLM

iHore/vLLM

Fork 0

Files

T

History

9eb9d9d395 [Perf] Support internal prefill checkpoints for Mamba prefix caching, 9%~25% TTFT improvement (#52789 )

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Ziming Huang <zelda.huanghuang@gmail.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Ziming Huang <zelda.huanghuang@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>

2026-08-22 10:32:40 -07:00

common

[DSV4] Implement Sequence Parallelism (#46789 )

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

deepseek_v4

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718 )

2026-08-21 17:47:49 -07:00

deepseek_v32

[Model] Remove unused DeepseekV32Indexer forward (#53021 )

2026-08-19 19:39:52 -07:00

dots3_note

[MM] Simplify _apply_hf_processor_main (#53275 )