Perplexity Fast Search trades 0.24 relevance points for much lower ranking compute
perplexity_ai · x · 2026-09-25
Perplexity detailed Fast Search, a new preset in its Search API that spends less compute on ranking than the default, aimed at day-to-day agentic tasks.
Internal tests on long-tail and broad-coverage queries show it scores only 0.24 points lower on relevance and about 3 percentage points lower on answer availability — a small quality trade for cheaper, faster search.
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