wonnx
wgpu
wonnx | wgpu | |
---|---|---|
18 | 195 | |
1,493 | 10,995 | |
4.6% | 3.2% | |
6.3 | 9.9 | |
about 1 month ago | about 23 hours ago | |
Rust | Rust | |
GNU General Public License v3.0 or later | Apache License 2.0 |
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/
[2]: https://github.com/webonnx/wonnx
-
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/
[2]: https://github.com/webonnx/wonnx
[3]: https://github.com/openxla/iree
-
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.
- WebGPU ONNX inference runtime written in Rust
-
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)
-
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).
[1] https://github.com/webonnx/wonnx
wgpu
-
GPU Compute in the Browser at the Speed of Native: WebGPU Marching Cubes
Oh look it's subgroup support landing last week: https://github.com/gfx-rs/wgpu/pull/5301
- 3D and 2D: Testing out my cross-platform graphics engine
- Warp Terminal is now available for Linux
- Linux version of Warp terminal is here
-
Building the DirectX shader compiler better than Microsoft?
And wgpu has been doing this for years. Things like descriptor indexing are not exposed to the web but used by Rust (mostly) engines on native.
https://wgpu.rs/
-
New Renderers for GTK
If they used https://wgpu.rs/ they would get directx and metal for free (:
-
Show HN: WebGPU Particles Simulation
IIRC it was delayed multiple times. I think the first intent to ship from chrome was before 100 but they kept pushing it off. Firefox still does not support it. There are projects like wgpu[0] that wrap provide a higher level API and I have used some projects using it with no issues. WFIW I didn't see any issue with OP's demo either.
[0] https://github.com/gfx-rs/wgpu
- Deno 1.39: The Return of WebGPU
-
How do I become a graphics programmer? – A guide from AMD Game Engineering team
wgpu, the Rust WebGPU implementation is the bee's knees. https://wgpu.rs/ You can use it beyond the web.
-
There is anything like wgpu.rs for Zig?
There is anything like wgpu.rs for Zig? wgpu.rs is an abstraction on top of Vulkan, Metal, DirectX, etc...
What are some alternatives?
stablehlo - Backward compatible ML compute opset inspired by HLO/MHLO
vulkano - Safe and rich Rust wrapper around the Vulkan API
onnx - Open standard for machine learning interoperability
tauri - Build smaller, faster, and more secure desktop applications with a web frontend.
tract - Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
glow - GL on Whatever: a set of bindings to run GL anywhere and avoid target-specific code
iree - A retargetable MLIR-based machine learning compiler and runtime toolkit.
rust-gpu - 🐉 Making Rust a first-class language and ecosystem for GPU shaders 🚧
burn - Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
bevy - A refreshingly simple data-driven game engine built in Rust
blaze - A Rustified OpenCL Experience
bgfx - Cross-platform, graphics API agnostic, "Bring Your Own Engine/Framework" style rendering library.