Perplexity 宣布开源 Lily，这是其为 Perplexity Computer 的混合计算构建的本地推理引擎。Lily 专为 Apple silicon 上的 Qwen3.6-35B-A3B 优化，使设备端算力不会成为 Computer 任务的瓶颈。详情见 https://www.perplexity.ai/hub/blog/optimizing-on-device-inference-for-apple-silicon
Perplexity@perplexity_aiPerplexity 宣布开源 Lily，这是其为 Perplexity Computer 的混合计算构建的本地推理引擎。Lily 专为 Apple silicon 上的 Qwen3.6-35B-A3B 优化，使设备端算力不会成为 Computer 任务的瓶颈。详情见 https://www.perplexity.ai/hub/blog/optimizing-on-device-inference-for-apple-silicon
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