wonnx
burn
wonnx | burn | |
---|---|---|
18 | 34 | |
1,493 | 4,845 | |
4.6% | - | |
6.3 | 8.9 | |
about 1 month ago | 5 months 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
burn
-
Burn 0.10.0 Released 🔥 (Deep Learning Framework)
Release Note: https://github.com/burn-rs/burn/releases/tag/v0.10.0
- Deep Learning Framework in Rust: Burn 0.10.0 Released
-
Why Rust Is the Optimal Choice for Deep Learning, and How to Start Your Journey with the Burn Deep Learning Framework
The comprehensive, open-source deep learning framework in Rust, Burn, has recently undergone significant advancements in its latest release, highlighted by the addition of The Burn Book 🔥. There has never been a better moment to embark on your deep learning journey with Rust, as this book will guide you through your initial project, providing extensive explanations and links to relevant resources.
-
Candle: Torch Replacement in Rust
Burn (deep learning framework in rust) has WGPU backend (WebGPU) already. Check it out https://github.com/burn-rs/burn. It was released recently.
- Burn – A Flexible and Comprehensive Deep Learning Framework in Rust
-
Announcing Burn-Wgpu: New Deep Learning Cross-Platform GPU Backend
For more details about the latest release see the release notes: https://github.com/burn-rs/burn/releases/tag/v0.8.0.
-
Are there any ML crates that would compile to WASM?
Tract is the most well known ML crate in Rust, which I believe can compile to WASM - https://github.com/sonos/tract/. Burn may also be useful - https://github.com/burn-rs/burn.
-
Any working wgpu compute example that would run in a browser?
We, the burn team, are working on the wgpu backend (WebGPU) for Burn deep learning framework. You can check out the current state: https://github.com/burn-rs/burn/tree/main/burn-wgpu
-
I’ve fallen in love with rust so now what?
Here is the project: https://github.com/burn-rs/burn
-
Is anyone doing Machine Learning in Rust?
Disclaimer, I'm the main author of Burn https://burn-rs.github.io.
What are some alternatives?
stablehlo - Backward compatible ML compute opset inspired by HLO/MHLO
candle - Minimalist ML framework for Rust
onnx - Open standard for machine learning interoperability
dfdx - Deep learning in Rust, with shape checked tensors and neural networks
tract - Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
tch-rs - Rust bindings for the C++ api of PyTorch.
iree - A retargetable MLIR-based machine learning compiler and runtime toolkit.
Graphite - 2D raster & vector editor that melds traditional layers & tools with a modern node-based, non-destructive, procedural workflow.
burn - Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
tract - Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference [Moved to: https://github.com/sonos/tract]
blaze - A Rustified OpenCL Experience
L2 - l2 is a fast, Pytorch-style Tensor+Autograd library written in Rust