Sari la conținut

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchProduse AI

analiza aiqbench

Perplexity's Photon demonstrates how optimizing retrieval infrastructure with Rust and custom data structures can drastically reduce AI search latency from 800 ms to 65 ms at p99. This shift from a maintained fork to an in-house engine highlights the critical role of low-level system engineering in scaling LLM applications, particularly when dealing with datasets that exceed available RAM. The release underscores that significant performance gains often come from architectural choices like adaptive posting lists and budgeted traversal rather than just model updates.
Sursă care acoperăMarkTechPost
Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

Perplexity Introduces Photon: A Rust-Based Retrieval Engine That Cuts p99 Latency From 800 ms to 65 ms

MarkTechPost4 min de cititArticolul și perspectiva sunt în engleză.

Perplexity has released Photon, an in-house retrieval and ranking engine written in Rust. It replaces an open-source engine Perplexity had forked for its AI-native search stack. Photon now handles retrieval and ranking for all production traffic. It also powers a new Fast Search mode in the Perplexity Search API. Perplexity reports single-call latency of 160 […] The post Perplexity Introduces Photon: A Rust-Based Retrieval Engine That Cuts p99 Latency From 800 ms to 65 ms appeared first on MarkTechPost.

Perplexity has released Photon, an in-house retrieval and ranking engine written in Rust. It replaces an open-source engine Perplexity had forked for its AI-native search stack. Photon now handles retrieval and ranking for all production traffic. It also powers a new Fast Search mode in the Perplexity Search API. Perplexity reports single-call latency of 160 ms at p50 and 230 ms at p95. Is it deployable? Yes, as a hosted API. Set search_type: "fast" on POST /search and…

Extras afișat conform termenilor RSS ai publicației · 78 cuvinte · textul integral și figurile sunt pe site-ul publicației

Subiecte conexe