vla.cpp

C++ inference runtime that runs open Vision-Language-Action robot policies from single GGUF files

PlatformWebfree

vla.cpp is an open-source C++ runtime for running Vision-Language-Action robot models, packaging each supported policy as a single self-contained GGUF file. It removes the need for Python or PyTorch at inference time and runs on CPU, Apple Silicon, CUDA and Intel GPUs, including Jetson-class boards. It is aimed at robotics teams deploying learned policies on constrained onboard compute.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of vla.cpp - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim vla.cpp to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether vla.cpp (or something else) actually fits.

Try a problem