Skip to content
Platform
Blogs
Docs
Join waitlist
Platform
Blogs
Docs
Join waitlist
Blog
Engineering notes from the Fenon team: systems, models and the measurements behind them.
26 October 2026
GR00T N1.7 runs 24.6% faster on H100 with Fenon.
Fenon runs NVIDIA’s GR00T N1.7 in 16.1 ms per action chunk on an H100. NVIDIA’s optimized TensorRT path takes 21.3 ms on the same machine.
7 minute read