Primary sourcevLLM
View sourceEvent ·Multi-source
vLLM AFD Plugin 发布,实现 MoE 推理 Attention-FFN 分离
vLLM 项目发布实验性插件 vLLM AFD Plugin,由 Ascend、vLLM、阶跃星辰、蚂蚁集团、FastAFD 联合开发。该插件针对 MoE 模型提出 Attention-FFN Disaggregation(AFD)方案,将注意力和专家/FFN 路径作为独立服务运行,支持独立扩缩容。AFD 运行在 NVIDIA GPU 和 Ascend NPU 上,无需 fork 即可使用相同 vLLM 服务接口。
Current read
vLLM 出了个新插件,把 MoE 推理的注意力层和专家层拆分部署,想分别扩缩容就方便了,支持 NVIDIA 和昇腾卡。
4 sources58° AI heatLast updated 2026/7/24 16:55:40
Evidence
4 sourcesRelated source 1LMSYS Org (SGLang)
View sourceRelated source 2NVIDIA AI
View sourceRelated source 3AI Will
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.