Perplexity's in-house Photon engine now handles all retrieval, replacing open-source search
perplexity_ai · x · 2026-09-25
Perplexity says its in-house Photon service now handles all retrieval and ranking across its products, replacing the open-source engine it previously used.
Photon stores the index in compact formats so each query reads and decodes only what it needs; disk reads are batched and run asynchronously to avoid blocking queries.
Related event: Perplexity Launches Fast Search, Powered by Its In-House Photon Engine(6 posts)→
More from Infra
- How GPUs really run deep learning: a primer on memory hierarchy and optimization — goyal__pramod · 2026-09-25
- VeriTile embeds Triton GPU kernels in Lean, with AI agents writing machine-checked correctness proofs — KaiyuYang4 · 2026-09-25
- Merge Gateway Launches Batch Inference at ~50% of Standard Prices — shensi · 2026-09-25
- New deep-dive article on scaling LLM inference in production — abhijithneil · 2026-09-25
- Lambda engineer shares local inference build rule: 27B models need 24-32GB VRAM — TheZachMueller · 2026-09-25
- Pokee AI demos 36B agent model running fully local on Snapdragon X2 Elite with 32GB RAM — Kyrannio · 2026-09-25