Lightweight inference library for ONNX files, written in C++. It can run Stable Diffusion XL 1.0 on a RPI Zero 2 (or in 298MB of RAM) but also Mistral 7B on desktops and servers. ARM, x86, WASM, RISC-V supported. Accelerated by XNNPACK.
I'm taking a crack at trying to integrate OnnxStream and OnnxStreamGUI (web) into the same Docker container (while also trying to learn PHP in the process) on my RPi 5 which also happens to have the new Hailo AI Hat that was released a little while ago.
Assuming I can pass the Hailo device into the container, I'm wondering if OnnxStream can use the hat easily or if that would require code changes.
I'm taking a crack at trying to integrate OnnxStream and OnnxStreamGUI (web) into the same Docker container (while also trying to learn PHP in the process) on my RPi 5 which also happens to have the new Hailo AI Hat that was released a little while ago.
Assuming I can pass the Hailo device into the container, I'm wondering if OnnxStream can use the hat easily or if that would require code changes.
Thanks!