Perplexity details why hybrid compute needs a purpose-built local engine like Lily
perplexity_ai · x · 2026-09-03
Perplexity's thread recaps why it open-sourced Lily: built for hybrid compute in Perplexity Computer, where cloud models and a local Mac model split the work and on-device inference must not bottleneck tasks. Lily is specialized for Qwen3.6-35B-A3B on Apple silicon, treating prefill and decode as distinct workloads unlike the general-purpose MLX-LM.
Related event: Perplexity Open-Sources Lily, a Local Inference Engine for Apple Silicon(8 posts)→
More from Infra
- Auction-based LLM routing paper finds fixed token pricing wastes 10%-71% in costs — _onionesque · 2026-10-18
- Running Ling 3.1 Flash (560B MoE, 25B Active) Across 4 DGX Sparks via llama.cpp RPC — BerryBlush_Rogers691 · 2026-10-18
- SGLang Summit sponsors jump from 11 to 36 in one week — ying11231 · 2026-10-18
- Oracle CDS hits record 300bps, called first AI trade domino after Barclays sell downgrade — arthurcolle · 2026-10-18
- Agent Coding Workflow Would Cost ~$40k/Month on API Pricing, Dev Reveals — ChrisRackauckas · 2026-10-18
- PS5LM: llama.cpp port turns a jailbroken PS5 into a home LLM server (500+ GitHub stars) — wateriscoding · 2026-10-18