Aravind Srinivas· @AravSrinivas · X·· 2026-09-03AI 评分60
AI 导读
Perplexity 开源本地推理引擎 Lily，专为 Apple Silicon 上的 Qwen3.6-35B-A3B 优化，用于支撑 Mac 应用新推出的混合计算功能，避免端侧算力成为 Computer 任务瓶颈。
正文 · 原文
We're open-sourcing Lily, Perplexity's local inference engine for serving models locally on Apple Silicon. This powers Perplexity's newly introduced hybrid compute feature for the Mac app.
Today we’re open-sourcing Lily, the local inference engine we built for hybrid compute in Perplexity Computer. Lily is specialized for Qwen3.6-35B-A3B on Apple silicon, built so on-device compute doesn’t bottleneck Computer tasks. Read more: https://www.perplexity.ai/hub/blog/optimizing-on-device-inference-for-apple-silicon在 X 查看被引用的帖子
来源：Aravind Srinivas · x.com