wonnx VS excalidraw

The two I know of are IREE and Kompute[1]. I'm not sure how much momentum the latter has, I don't see it referenced much. There's also a growing body of work that uses Vulkan indirectly through WebGPU. This is currently lagging in performance due to lack of subgroups and cooperative matrix mult, but I see that gap closing. There I think wonnx[2] has the most momentum, but I am aware of other efforts.

[1]: https://kompute.cc/

[2]: https://github.com/webonnx/wonnx

To a first approximation, Kompute[1] is that. It doesn't seem to be catching on, I'm seeing more buzz around WebGPU solutions, including wonnx[2] and more hand-rolled approaches, and IREE[3], the latter of which has a Vulkan back-end.

[1]: https://kompute.cc/

[2]: https://github.com/webonnx/wonnx

[3]: https://github.com/openxla/iree

There's also a third-party WebGPU implementation: https://github.com/webonnx/wonnx

By experimental I meant e.g. using WGPU to run compute shaders like wonnx, which is working fine but only on a very restricted set of devices and browsers.

https://news.ycombinator.com/item?id=35696031 ... TIL about wonnx: https://github.com/webonnx/wonnx#in-the-browser-using-webgpu...

microsoft/onnxruntime: https://github.com/microsoft/onnxruntime

Apache/arrow has language-portable Tensors for cpp: https://arrow.apache.org/docs/cpp/api/tensor.html and rust: https://docs.rs/arrow/latest/arrow/tensor/struct.Tensor.html and Python: https://arrow.apache.org/docs/python/api/tables.html#tensors https://arrow.apache.org/docs/python/generated/pyarrow.Tenso...

Fwiw it looks like the llama.cpp Tensor is from ggml, for which there are CUDA and OpenCL implementations (but not yet ROCm, or a WebGPU shim for use with emscripten transpilation to WASM): https://github.com/ggerganov/llama.cpp/blob/master/ggml.h

Are the recommendable ways to cast e.g. arrow Tensors to pytorch/tensorflow?

FWIU, Rust has a better compilation to WASM; and that's probably faster than already-compiled-to-JS/ES TensorFlow + WebGPU.

What's a fair benchmark?

wonnx has done some fantastic work in this regard, so that's where we plan to start once we get there. In terms of general discussion of alternate backends, see this issue.

> GPU in other ways, such as training ML models and then using them via an inference engine all powered by your local GPU?

Have a look at wonnix https://github.com/webonnx/wonnx

A WebGPU-accelerated ONNX inference run-time written 100% in Rust, ready for native and the web

Looking forward to your WebGPU ML runtime! Also, why not contribute back to WONNX? (https://github.com/webonnx/wonnx)

You can indeed perform inference using WebGPU (see e.g. [1] for GPU-accelerated inference of ONNX models on WebGPU; I am one of the authors).

The point made above is that WebGPU can only be used for GPU's and not really for other types of 'neural accelerators' (like e.g. the ANE on Apple devices).

[1] https://github.com/webonnx/wonnx

ExcaliDraw

However, Notion and Obsidian can only help you write documentation. Well, how about some visuals? Let's talk about Excalidraw.

Fun fact: I used GA in Excalidraw, and it's still powering some of the interactions! https://github.com/excalidraw/excalidraw/blob/master/package...

I was happy to find out recently that there is a way to make Mermaid diagrams WYSIWYG / drag and drop editable that the open source https://excalidraw.com has and did I mention it's open source!? With a LLM, you can go full loop back to Mermaid again after a few rounds of manual editing. "What a time to be alive!"

I'm working on a personal project and found myself looking for an alternative to Postman/Insomnia this morning. This made me realize i've been using the same tools for so long for work (mobile development, finance) that this project may be a good time to try out some new things.

Here are a few tools that i've been using lately that I really enjoy:

https://pocketbase.io/ - A dead-simple self-hosted firebase/supabase-like "backend in a box" using golang and sqlite. So far i've been really impressed. I've gone the route of extending the base offering with more go code and am really enjoying the experience.

https://excalidraw.com/ - An open source whiteboarding tool. Slick to use and after learning some keybinds I've gotten pretty fast at throwing together diagrams to explain things to people on my team. The killer piece though is that the filetype is just json, so I can source control my diagrams. Even better, their "export to png" function has a box to embed the json data _into_ the png, allowing me to slap the diagram in places that only accept images (think confluence) and still be able to change the diagram later if needed. 10/10.

https://docs.gitlab.com/ee/ci/ - Gitlab's CI/CD toolset is really impressive, and I've gotten really intimate with it's deeper features over the past year. I'd be curious though to hear from someone who's familiar with it vs it's competitors.

Sketch easy and go back to work...

https://excalidraw.com/