ReleasesSep 3, 2026 · 03:542 sources

Perplexity Open-Sources Lily Engine for 1.35x Faster Apple Silicon Decode

From huggingnews.com

Image: huggingnews.com
AI;DR

The local inference engine Lily supports the Qwen3.6-35B-A3B model to enable hybrid compute on Mac devices. Benchmarks conducted on an M5 Max MacBook Pro show that Lily delivers 1.35x higher decode throughput and 1.23x higher prefill throughput than MLX-LM across 10 prompt lengths and 10 decode contexts. Perplexity released the source code for the engine to ensure on-device processing does not bottleneck tasks within its Computer agent system.

Read the sourceSign in to suggest

Sources

+ 1 more
  1. SUPPORT@perplexity_ai“averaging 1.23× higher prefill throughput and 1.35× higher decode throughput”x.com

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today