PCIe Co-Processing
Run inference from a host connected to a Modalix PCIe Card. Use these tutorials in order.
The PCIe host API accepts either a model-ready tensor or decoded image pixels. Tensor mode keeps preprocessing on the host. I...
Synchronous `run()` is ideal for a first inference, but it waits for each result before submitting the next image. A producer...
A Modalix PCIe Card exposes queues 0 through 3. Each active `Model` owns one queue, so independent models can execute concurr...
The default PCIe route sends FP32 tensors to the card, where the input is quantized, the MLA runs, and the output is dequanti...
`Tensor::from_external()` lets a C++ application wrap an existing contiguous allocation instead of copying it into a new host...