audiovention

Accelerate docker wasm workloads

1

Hi, that's a really awesome project you have created! I've been thinking a lot lately on the in-browser virtualization topics, with my dream to run a full-blown linux distro with...

Using dashboardUrl does not function properly

5

I followed the instructions and deployed packages/dashboard in my cloudflare pages. The initial page loads fine, but navigating is impossible as the routing doesn't function properly when dashboardUrl is specified,...

I'm using ggml to train a small-ish network. I have a bunch of simplistic view operations (just reducing the leading dimension of a tensor), and I noticed the view operation...

Webgpu backend

2

Hi all, I have whipped up a very quick and dirty webgpu backend for ggml. This is by no means ready for merging, it's been written in a day, supports...

I'm working on a project which needed those operations. tanh was parallelized in the same manner as other unary ops ADD is generalized to allow for ggml_can_repeat constraint, instead of...

Using memcpy on tensor data when the tensor is not contiguous

1

I see in some places in the codebase the implicit assumption that a tensor's memory is contiguous, without any checks/asserts. For example "ggml_metal_set_tensor" (get_tensor as well) has: `memcpy((void *) ((uint8_t...

sgemm performance

2

hey man, very cool repo. I've been working on some ML stuff with webgpu as well lately, and so I've been playing around with sgemm kernels as well. I took...

Enhancement: allow async exception handlers

5

### Summary I want to log my exceptions, but also log the request headers and body when an exception occurs. Basically what LoggingMiddlewareConfig does, but only when an exception occurs....