Perplexity发布多项开源贡献
Perplexity一口气发布了7个开源项目，从多模态模型到本地推理引擎，每个都有具体性能数据。
Perplexity近期发布了多项开源项目。pplx-decider-v1-27b是多模态决策模型，在11个基准测试中平均得分85.7%，领先Jev模型。pplx-embed-v2-context-9b-preview是上下文嵌入模型，在ConTEB和turbopuffer context-bench上表现最佳。Lily是针对Apple Silicon的本地推理引擎，使用Rust和自定义Metal内核，比MLX-LM快1.23倍预填充和1.35倍解码。
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! 💬 20 🔄 24 ❤️ 352 👀 28872 📊 61 ⚡
