PulseAugur
实时 07:30:21
English(EN) Perplexity Open Sources Lily: A Rust + Metal Inference Engine for Qwen3.6-35B-A3B on Apple Silicon

Perplexity 开源适用于 Apple Silicon 的 Lily 推理引擎

Perplexity 已开源 Lily,这是一款使用 RustMetal 构建的专用推理引擎,用于在 Apple Silicon 上运行 Qwen3.6-35B-A3B 模型。该引擎通过紧密集成模型结构、执行计划和内核选择,绕过 PyTorchMLX 等传统框架,旨在实现高性能。与现有实现相比,Lily 在预填充和解码操作方面均实现了显著的加速,尤其是在具有大量统一内存的 Mac 上处理长上下文时。 AI

影响 使得在 Apple 硬件上进行更高效的本地 LLM 推理成为可能,有望改善 Perplexity 产品用户体验。

排序理由 针对特定模型和硬件的专用推理引擎的开源。

在 MarkTechPost 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Perplexity 开源适用于 Apple Silicon 的 Lily 推理引擎

本文如何被排名

Signal score
43 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
针对特定模型和硬件的专用推理引擎的开源。
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准

报道来源 [1]

  1. MarkTechPost TIER_1 English(EN) · Asif Razzaq ·

    Perplexity 开源 Lily:一款用于 Apple Silicon 上 Qwen3.6-35B-A3B 的 Rust + Metal 推理引擎

    <p>Perplexity has open sourced Lily, the local inference engine behind Hybrid Compute in Perplexity Computer. Built in Rust with custom Metal kernels for one model on one chip family, it averages 1.23x MLX-LM's prefill throughput and 1.35x its decode throughput on a 40-core, 128 …