Tommy van der Vorst

> Another question somewhat related: I want to implement a custom op [dcnv2](https://github.com/jinfagang/DCNv2_latest/blob/master/src/cuda/dcn_v2_im2col_cuda.cu), it has some pre/post process steps around the cuda function. I looked through wonnx code and cannot...

Another option would be to slightly change the compiler code such that it allows invoking different functions in a shader (with their own thread counts) in sequence. This should be...

@zimond sure, I will be happy to review PRs! The question is how to implement this without overcomplicating things. My first thought was to change `NodeTemplate` to accept an (optional)...

Hm, good point. In this case perhaps splitting the op into multiple 'internal' ops (each with their own shader, buffer) is better?

@zimond sounds like a good idea - you might also move these to `wonnx-preprocessing` which has some other bells and whistles that are not needed by all users.

> Hi there, > > I read that wonnx can use gpu through graphics apis like metal and vulkan. Just wondering, does it default to cpu inference if there is...

As far as I am ware WebGPU in browsers is still stuck on security hesitations / implementation of proper sandboxing. The spec (esp. regarding WGSL syntax) has matured over the...

NB, I am curious whether browsers will be implementing software emulated WebGPU in absence of hardware GPU (e.g. based on Lavapipe?). In that case wonnx would universally run (albeit a...

The `wonnx-cli` crate actually implements a basic wrapper around both wonnx in [gpu.rs](https://github.com/webonnx/wonnx/blob/master/wonnx-cli/src/gpu.rs) and tract in [cpu.rs](https://github.com/webonnx/wonnx/blob/master/wonnx-cli/src/cpu.rs). Each contains an implementation for `trait Inferer` (https://github.com/webonnx/wonnx/blob/master/wonnx-cli/src/types.rs#L224).

> Yeah, I saw that - that's awesome, that's already getting us quite far. Are there any plans to extract that into a crate of its own? No but it...