GitHub · C++
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
- Stars
- 817
- Forks
- 107
- Stars gained in 24 hours
- +13
- Forks gained in 24 hours
- +1
Topics: cuda, cuda-kernels, gr00t, gr00t-n1-6-3b, jetson, jetson-orin, jetson-thor, motus, pi, pi05
Latest data point: Nov 20, 2026 · 817 stars · 107 forks