wonnx
gpuweb
Our great sponsors
wonnx | gpuweb | |
---|---|---|
18 | 56 | |
1,424 | 4,534 | |
4.9% | 2.1% | |
6.5 | 9.0 | |
10 days ago | about 17 hours ago | |
Rust | Bikeshed | |
GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
wonnx
-
Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'
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/
-
VkFFT: Vulkan/CUDA/Hip/OpenCL/Level Zero/Metal Fast Fourier Transform Library
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/
-
Onnx Runtime: “Cross-Platform Accelerated Machine Learning”
There's also a third-party WebGPU implementation: https://github.com/webonnx/wonnx
-
Are there any ML crates that would compile to WASM?
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.
-
PyTorch Primitives in WebGPU for the Browser
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?
-
rustformers/llm: Run inference for Large Language Models on CPU, with Rust 🦀🚀🦙
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.
-
I want to talk about WebGPU
> 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
-
Chrome Ships WebGPU
Looking forward to your WebGPU ML runtime! Also, why not contribute back to WONNX? (https://github.com/webonnx/wonnx)
This makes running larger machine learning models in the browser feasible - see e.g. https://github.com/webonnx/wonnx (I believe Microsoft's ONNXRuntime.js will also soon gain a WebGPU back-end).
-
OpenXLA Is Available Now
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).
gpuweb
-
WebGPU now available for testing in Safari Technology Preview
People keep spreading this incredibly misleading statement, and yours is even more misleading (suggesting Apple opposed a 'GPU WASM')
By all accounts, Apple's /only/ stance was that if WebGPU used SPIR-V it would be a non-starter for them, due to ongoing legal issues between Apple and Khronos.
Apple actually proposed WebHLSL in collaboration with Microsoft, to have HLSL be the standard.
Mozilla employee's stance[0] was that SPIRV was too low level, did not fit with the goals of WebGPU portability and security, and expressed concern that Khronos may add functionality to SPIRV they cannot support in WebGPU like raytracing instructions .. 'So we'd always be on the verge of forking SPIR-V in some way.'
It was also noted by many people that even if a bytecode format was used, it would still have to be translated to the target (HLSL/DXIL, MSL, etc.) in almost the same way a text format would.
Nobody proposed a 'GPU WASM equivalent' or an alternative bytecode format.
The hard truth is that shader compilation is a fucking nightmare, people do not realize how bad it is across the different native APIs. SPIR-V is good, but it doesn't solve that - and presents other challenges if you are a web browser API. Vulkan and SPIRV are not the golden goose many make them out to be.
[0] https://github.com/gpuweb/gpuweb/issues/847#issuecomment-642...
-
Show HN: WebGPU Particles Simulation
Yes it is still a bit new. WebGPU is not finished and is still being worked on: https://webgpu.io/
-
Capturing the WebGPU Ecosystem
There's a proposal for a "WebGPU compatibility mode" which also works on older devices:
WebGPU currently doesn't support the "bindless" resource access model (see: https://github.com/gpuweb/gpuweb/issues/380).
The "max number of sampled texture per shader stage" is a runtime device limit, and the minimal value for that seems to be 16. So texture atlasses are still a thing in WebGPU.
-
Why aren't we using highly efficient int8 calcualtions in quants? (maybe eli14?)
There's even an implementation under discussion to have the dp4a instruction added to WebGPU (https://github.com/gpuweb/gpuweb/issues/2677)
- WebGPU – All of the cores, none of the canvas
- [Rust_Gamedev] WGSL est-il un bon choix?
-
I want to talk about WebGPU
Shared memory, yes, with the goodies: atomics and barriers. We rely on that heavily in Vello, so we've pushed very hard on it. For example, WebGPU introduces the "workgroupUniformLoad" built-in, which lets you broadcast a value to all threads in the workgroup while not introducing potential unsafety.
Tensor cores: I can't say there are plans to add it, but it's certainly something I would like to see. You need subgroups in place first, and there's been quite a bit of discussion[1] on that as a likely extension post-1.0.
- Chrome ships WebGPU (available by default in Chrome 113)
What are some alternatives?
wgsl.vim - WGSL syntax highlight for vim
pyodide - Pyodide is a Python distribution for the browser and Node.js based on WebAssembly
noclip.website - A digital museum of video game levels
BestBuy-GPU-Bot - BestBuy Bot is an Add to cart and Auto Checkout Bot. This auto buying bot can search the item repeatedly on the ITEM page using one keyword. Once the desired item is available it can add to cart and checkout very fast. This auto purchasing BestBuy Bot can work on Firefox Browser so it can run in all Operating Systems. It can run for multiple items simultaneously.
wgpu-rs - Rust bindings to wgpu native library
WASI - WebAssembly System Interface
naga - Universal shader translation in Rust
webgpu-wgsl-hello-triangle - An example of how to render a triangle with WebGPU using WebGPU Shading Language - the "Hello world!" of computer graphics.
Flutter - Flutter makes it easy and fast to build beautiful apps for mobile and beyond
stablehlo - Backward compatible ML compute opset inspired by HLO/MHLO
wgsl-cheat-sheet - Cheat sheet for WGSL syntax for developers coming from GLSL.
tract - Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference