Perplexity开源Lily本地推理引擎

Today we’re open-sourcing Lily, the local inference engine we built for hybrid compute in Perplexity...

精选理由

Perplexity开源了专为Apple芯片优化的Lily推理引擎,解决Qwen3.6-35B-A3B的本地计算瓶颈问题。

AI 摘要

Perplexity发布了名为Lily的本地推理引擎,专为Qwen3.6-35B-A3B模型在Apple硅芯片上优化。该引擎解决了设备端计算瓶颈问题,支持混合计算架构。Lily是Perplexity Computer的核心组件,现已开源。

图片来源 · Perplexity
原文 · Perplexity

Today we’re open-sourcing Lily, the local inference engine we built for hybrid compute in Perplexity...

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: perplexity.ai/hub/blog/optim… 💬 1 🔄 0 ❤️ 4 👀 1449 📊 1 ⚡