Encrypted GPT-2 speedrun challenges FHE inference: best is 3.031 s/token, goal sub-1s
tensorqt · x · 2026-10-27
GladiaLab launched the "Encrypted GPT-2 Speedrun", aiming to push fully homomorphic encryption (FHE) inference of GPT-2 from the current best of 3.031 s/tok below the 1.0 s/tok barrier — closing a gap of roughly 4,655× versus plaintext inference.
Rules were released as a thread and the effort is co-signed by crypto VC Paradigm. Teams interested in private inference and FHE optimization can join and compete on the leaderboard.
More from Infra
- AWS tutorial: fleet-wide edge CV model lifecycle with SageMaker SDK v3, ~$0.07 per run — AWS ML Blog · 2026-10-27
- Qwen3.8-27B hits 40 tok/s on Jetson Thor with INT4 + MTP, accuracy beats FP16 — No-Dragonfly6246 · 2026-10-27
- Celesto launches CI runners nearly 90% cheaper than GitHub Actions, with agent sandboxes — aniketmaurya · 2026-10-27
- Supabase founders on rebuilding the backend for a billion AI-built apps — Latent Space · 2026-10-27
- AW-0 runs at 230ms on a single RTX 5090, 2.4x faster than autoregressive code planning — trevordarrell · 2026-10-27
- Site tracks US city council topics: data centers rank only behind pickleball courts — zakkohane · 2026-10-27