Illustration: the project’s public image, pixelated by RepoMasters. Credits
BetaRare

flashrt-project/FlashRT

FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST. Also support llm e.g, qwen3.6-27B

Owner
flashrt-project (organization)
Stars
Stars: 778
Forks
Forks: 103
Language
C++
License
Apache-2.0
Created
2026
Topics
cudacuda-kernelsrealtime-inferencerealtime-vlagr00tgr00t-n1-6-3bpipi05vlaqwen
Tier
Beta (700 to 1,999 ★) What this tier means
View on GitHub

Nearby in C++

All C++ repos