v0.25.0
# 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
关键事实
# 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
阅读原文
自动收录自 vLLM 发布记录 的公开订阅信息；请以原始出处为准。
本站不保存或展示该来源的全文。
前往原始出处阅读 ↗