Perplexity 开源七个项目，含多模态决策模型与 Apple 芯片推理引擎
a few open source contributions from perplexity recently:
Perplexity 近期开源了七个项目。pplx-decider-v1-27b 是多模态决策模型，在 11 项基准上平均 85.7%，领先 Jev；pplx-embed-v2-context-9b-preview 为上下文嵌入向量模型，在 ConTEB 和 turbopuffer context-bench 上表现最佳。此外还有面向 Apple silicon 的本地推理引擎 Lily，用 Rust 加自定义 metal kernel 实现，在 M5 Max 上 prefill 比 MLX-LM 快 1.23 倍、decode 快 1.35 倍；0.6B 端侧 PII 分类器 PII-Tracer 及配套 PII-TRACE 基准；面向深度研究智能体的 WANDR 基准；笔记本与工作站智能体检测响应工具 Numbat；以及只读供应链扫描器 Bumblebee。
正文
当前显示原文，中文全文译文尚未就绪。
a few open source contributions from perplexity recently:
•pplx-decider-v1-27b: SoTA multimodal decision model. 85.7% average across 11 benchmarks, ahead of Jev. •pplx-embed-v2-context-9b-preview: SoTA contextual embeddings, best on ConTEB and turbopuffer context-bench. •Lily: local inference engine for Apple silicon. rust plus custom metal kernels, no pytorch or mlx. 1.23x faster prefill and 1.35x faster decode than MLX-LM on an M5 Max •PII-Tracer: 0.6B on-device PII classifier that decides when a hybrid compute task stays on your Mac. beats OpenAI’s Privacy Filter on all 5 public benchmarks. also released with the PII-TRACE benchmark: 13k conversations in 13 languages •WANDR: benchmark for wide and deep research agents. 500 tasks needing 170k source-backed records •Numbat: agent detection and response for laptops and workstations. 52 rules, single go binary for macOS, linux and windows •Bumblebee: read-only supply chain scanner for dev machines. covers packages, MCP configs, and editor and browser extensions.
a lot more open source contributions coming soon!