Repository navigation
Tags
Tags
[Bugfix][Core] Apply dense prefix cache default to hybrid models (vll… …m-project#55861) Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
[Core] Default prefix_cache_retention_interval to dense for Mamba + E… …AGLE (vllm-project#55760) Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
[Bugfix] Avoid sync in TRT-LLM ragged prefill Generated-by: Codex <codex@openai.com> Signed-off-by: Codex <codex@openai.com>
[CI] Remove deleted nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF1… …6 and its arch aliases (vllm-project#55026) Signed-off-by: khluu <khluu000@gmail.com> Co-authored-by: Kimi Code <noreply@moonshot.cn>
[Bugfix][Multimodal] Handle prefix-covered items in SHM worker cache (v… …llm-project#54994) Signed-off-by: waizuichougou <2082431897@qq.com> Signed-off-by: Nick Hill <nickhill123@gmail.com> Co-authored-by: Nick Hill <nickhill123@gmail.com>
[Bugfix] Handle padded routes in CUTLASS MoE permutations (vllm-proje… …ct#54747) Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com> Signed-off-by: Yongye Zhu <zyy1102000@gmail.com> Co-authored-by: Codex <codex@openai.com> Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
[Tools][Recipes] Improve sweep recommendations and short-alias parsing ( vllm-project#53946) Signed-off-by: louie-tsai <louie.tsai@intel.com>
PreviousNext