VkFFT
wonnx
Our great sponsors
VkFFT | wonnx | |
---|---|---|
37 | 18 | |
1,443 | 1,487 | |
- | 6.8% | |
8.1 | 6.5 | |
about 1 month ago | 30 days ago | |
C++ | Rust | |
MIT License | 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.
VkFFT
-
[P] - VkFFT now supports quad precision (double-double) FFT computation on GPU
Hello, I am the creator of the VkFFT - GPU Fast Fourier Transform library for Vulkan/CUDA/HIP/OpenCL/Level Zero and Metal. In the latest update, I have added support for quad-precision double-double emulation for FFT calculation on most modern GPUs. I understand that modern ML is going in the opposite low-precision direction, but I still think that it may be useful to have this functionality at least for some prototyping and development of concepts.
- VkFFT now supports quad precision (double-double) FFT computation on GPU
-
VkFFT: Vulkan/CUDA/Hip/OpenCL/Level Zero/Metal Fast Fourier Transform Library
Not quite what I asked for, but close enough for now...
https://github.com/DTolm/VkFFT/discussions/126
-
Implementing complex numbers (and FFT) elegantly with just algebraic datatypes (no machine floats)
Source - I have made a somewhat functional programming-like FFT library (https://github.com/DTolm/VkFFT/tree/develop) which also operates on abstract data containers. Maybe it can be interesting to you from the algorithmic point of view.
-
how does Vulkan compare to CUDA?
VkFFT is a use-case I've heard of where Vulkan-Compute is faster than its Cuda and OpenCL counter-part: https://github.com/DTolm/VkFFT
-
VkFFT now supports Apple Metal API - M1 Pro GPU FFT benchmarking
Hello, I am the creator of the VkFFT - GPU Fast Fourier Transform library for Vulkan/CUDA/HIP/OpenCL and Level Zero. In the latest update, I have added support for Apple Metal API, which will allow VkFFT to run natively on modern Apple SoC. I have tested it on MacBook Pro with an M1 Pro 8c CPU/14c GPU SoC single precision on 1D batched FFT test of all systems from 2 to 4096. Achieved bandwidth is calculated as 2*system size divided by the time taken per FFT - minimum memory that has to be transferred between DRAM and GPU:
-
Any good compute shader tutorials?
Another possible project to look at is https://github.com/DTolm/VkFFT
- VkFFT now supports Rader's algorithm - A100 and MI250 benchmarks: Part 2
- VkFFT now supports Rader's algorithm - A100 and MI250 benchmarks
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
What are some alternatives?
wgpu - Cross-platform, safe, pure-rust graphics api.
stablehlo - Backward compatible ML compute opset inspired by HLO/MHLO
kompute - General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for advanced GPU data processing usecases. Backed by the Linux Foundation.
onnx - Open standard for machine learning interoperability
rust-gpu - 🐉 Making Rust a first-class language and ecosystem for GPU shaders 🚧
tract - Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
cuda-samples - Samples for CUDA Developers which demonstrates features in CUDA Toolkit
iree - A retargetable MLIR-based machine learning compiler and runtime toolkit.
rocFFT - Next generation FFT implementation for ROCm
burn - Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
xNVMe - Portable and high-performance libraries and tools for NVMe devices as well as support for traditional/legacy storage devices/interfaces.
blaze - A Rustified OpenCL Experience