wonnx
WebKit
wonnx | WebKit | |
---|---|---|
18 | 151 | |
1,493 | 7,456 | |
4.6% | 1.7% | |
6.3 | 10.0 | |
about 1 month ago | 2 days ago | |
Rust | ||
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/
[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
WebKit
-
GPU Compute in the Browser at the Speed of Native: WebGPU Marching Cubes
Multiple engineers are working on adding it back: https://github.com/WebKit/WebKit/pulls?q=is%3Apr+is%3Aclosed...
-
HTML Streaming and DOM Diffing Algorithm
Since 2023 Chrome announced the View Transition API, and it looks like Safari is also going to support it soon.
-
Towards memory safety with ownership checks for C
One heap per type.
Here’s an allocator optimized for that use case.
https://github.com/WebKit/WebKit/blob/main/Source/bmalloc/li...
-
Bun, JavaScript, and TCO
To use this in Bun, you’d have to start Bun with the environment variable “BUN_JSC_useDollarVM=1” and then $vm.createBuiltin(mySourceCodeString)
When using this intrinsic, if any of the arguments are incorrect or it cannot otherwise enable it, the entire process will probably crash. In debug builds of JSC it will have a nicer assertion failure but that is not enabled in release builds
Example code: https://github.com/WebKit/WebKit/blob/17351231b4dedb62d81721...
also happy to answer any questions about Bun
-
Show HN: Rem: Remember Everything (open source)
Ah, good, let me introduce you to the wonderful world of the Chrome Devtools Protocol! (fka Chrome Remote Debugging Protocol)
I love this API for almost everything browser related. I built my RBI product atop this (BrowserBox: https://dosyago.com), and I think it's a drastically underrated API.
Also, it works out of the box in Edge, Brave, Chromium, and many parts of CRDP are supported by Firefox and Safari^1
1: See for example: https://github.com/WebKit/webkit/tree/main/Source/JavaScript...
- WebGPU now available for testing in Safari Technology Preview
-
Disabling iOS Personalized Ads tells kernel to kill daemon every 3 seconds
No, it's unrelated.
https://github.com/WebKit/WebKit/commit/064df1a9f395f8c6e32c...
- Apple's Safari browser is still vulnerable to Spectre attacks
-
Replacing WebRTC: real-time latency with WebTransport and WebCodecs
It's being worked on now: https://github.com/WebKit/WebKit/pull/17320
-
iLeakage: Browser-Based Timerless Speculative Execution Attacks on Apple Devices
It is different. The cross-site navigation flag is a couple of years old. It was enabled by default for iOS in November 2018 for example https://github.com/WebKit/WebKit/commit/e191fc8c412850cb9fd0...
What are some alternatives?
stablehlo - Backward compatible ML compute opset inspired by HLO/MHLO
chromium - The official GitHub mirror of the Chromium source
onnx - Open standard for machine learning interoperability
otter-browser - Otter Browser aims to recreate the best aspects of the classic Opera (12.x) UI using Qt5
tract - Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
cname-trackers - This repository contains a list of popular CNAME trackers
iree - A retargetable MLIR-based machine learning compiler and runtime toolkit.
fingerprintjs - Browser fingerprinting library. Accuracy of this version is 40-60%, accuracy of the commercial Fingerprint Identification is 99.5%. V4 of this library is BSL licensed.
burn - Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
gecko-dev - Read-only Git mirror of the Mercurial gecko repositories at https://hg.mozilla.org. How to contribute: https://firefox-source-docs.mozilla.org/contributing/contribution_quickref.html
blaze - A Rustified OpenCL Experience
uBlock-Safari - uBlock Origin - An efficient blocker for Chromium, Firefox, and Safari. Fast and lean.