Perplexity ships Photon, a Rust retrieval engine cutting latency to 160ms p50 and costs 68%
inductionheads · x · 2026-09-25
- Photon: Perplexity's new retrieval and ranking engine optimized for agentic workloads at web scale, built entirely in Rust by a small team plus $300K of tokens
- Runs on 20% fewer machines while storing 2.5x more data per document vs the old system
- Powers new Fast Search in the Perplexity Search API: 160ms p50 / 230ms p95 latency (95% of results in ≤230ms)
- 68% lower cost per task across six agentic benchmarks at the same quality
Related event: Perplexity Launches Fast Search Powered by Homegrown Photon Engine(9 posts)→
More from Infra
- Google's Project Suncatcher flies TPU prototype satellite on SpaceX Transporter-18 — Miles_Brundage · 2026-09-25
- YC-backed Isoquant launches GLM-5.3-Flash inference at $0.07/M with 452ms TTFT — ycombinator · 2026-09-25
- Nemotron 3 Speaker Diarization Ported to Apple Silicon via Core ML and MLX — ivan_digital · 2026-09-25
- Strangely, GPU matmuls run faster on 'predictable' data: Horace He explains — goyal__pramod · 2026-09-25
- PyTorch announces ExecuTorch Hackathon in San Francisco, Oct 17-18, with three device tracks — PyTorch · 2026-09-25
- Speculation: GPT-6 Luna/Sol efficiency lean hints at Cerebras 1000 tok/s inference economics — brandon_galang · 2026-09-25