aifollow.news 搜索
返回 vLLM 发布记录
vLLM 发布记录· · 仅日期

v0.25.0

来源摘录

# vLLM v0.25.0 Release Notes ## Highlights This release features 558 commits from 232 contributors (64 new)! * **Model Runner V2 is now the default for all dense models** (#44443). Building on quantized-model support from the previous release, MRv2 is now the standard execution path, with new support for EVS (#46535), realtime embeddings (#46762), prefix caching for Mamba hybrid models (#42406), multimodal-prefix bidirectional attention (#46942), and dynamic speculative decoding compatible with full CUDA graphs (#45953). * **PagedAttention has been removed** (#47361). The legacy attention implementation is deleted now that V1/MRv2 backends ar

完整正文暂未获取。

前往原始出处阅读
发现内容有误?提交纠错