Denis Yarats(@denisyarats):we are open-sourcing Lily, lightweight local inference engine for Apple Silicon, optimized directly for the Qwen MoE architecture and implemented on top of custom Metal kernels and a compact Rust runtime that manages both the session state and the generation loop. we carefully optimized the engine around Qwen's exact architecture and dimensions: matrix/vector kernels for prefill/decode, minimal data movement across expert, attention, and recurrent paths, and tiles and layouts tuned to the live workload. with these optimizations we achieve 1.23x faster prefill and 1.35x faster decode than MLX-LM on Qwen3.6-35B-A3B Q4! for more details, check out our blog and code: code: https://t.co/JMews5uPXY blog:

2026.09.02 20:11

we are open-sourcing Lily, lightweight local inference engine for Apple Silicon, optimized directly for the Qwen MoE architecture and implemented on top of custom Metal kernels and a compact Rust runtime that manages both the session state and the generation loop. we carefully optimized the engine around Qwen's exact architecture and dimensions: matrix/vector kernels for prefill/decode, minimal data movement across expert, attention, and recurrent paths, and tiles and layouts tuned to the live workload. with these optimizations we achieve 1.23x faster prefill and 1.35x faster decode than MLX-LM on Qwen3.6-35B-A3B Q4! for more details, check out our blog and code: code: blog:

Perplexity@perplexity_ai

2026.09.02 20:04

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: