AIMarkTechPostabout 2 hours ago
Perplexity Open Sources Lily Inference Engine
5 min read
Perplexity open sourced Lily, the Rust and Metal inference engine behind Hybrid Compute in Perplexity Computer. It runs Qwen3.6-35B-A3B on Apple Silicon without PyTorch or MLX. A standalone demo is public in the pplx-garden repository.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
