wgpu-mm | pygfx | |
---|---|---|
1 | 3 | |
50 | 361 | |
- | 5.0% | |
8.7 | 8.8 | |
about 2 months ago | 3 days ago | |
WGSL | Python | |
- | BSD 2-clause "Simplified" License |
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.
wgpu-mm
-
Chrome Ships WebGPU
This is very exciting! (I had suspected it would slip to 114)
WebGPU implementations are still pretty immature, but certainly enough to get started with. I've been implementing a Rust + WebGPU ML runtime for the past few months and have enjoyed writing WGSL.
I recently got a 250M parameter LLM running in the browser without much optimisation and it performs pretty well! (https://twitter.com/fleetwood___/status/1638469392794091520)
That said, matmuls are still pretty handicapped in the browser (especially considering the bounds checking enforced in the browser). From my benchmarking I've struggled to hit 50% of theoretical FLOPS, which is cut down to 30% when the bounds checking comes in. (Benchmarks here: https://github.com/FL33TW00D/wgpu-mm)
I look forward to accessing shader cores as they mentioned in the post.
pygfx
-
Emerging Rust GUI libraries in a WASM world
https://github.com/kushalkolar/fastplotlib
Alternatively, try pygfx for ThreeJS graphics in Python leveraging wgpu. It works great in Notebooks through notebook-rfb. https://github.com/pygfx/pygfx
If you're adventurous, figure out how to make pygfx work with webgpu via wasm
-
Chrome Ships WebGPU
FYI you can already use webgpu directly in python, see https://github.com/pygfx/wgpu-py for webgpu wrappers and https://github.com/pygfx/pygfx for a more high level graphics library
-
Extending Python with Rust
Rather than using matplotlib, you could try either pygfx (https://github.com/pygfx/pygfx) or fastplotlib (https://github.com/kushalkolar/fastplotlib) to make higher performance graphics using Python.
However, it won't solve your problem of Python not being fast enough doing the calculations.
What are some alternatives?
SHA256-WebGPU - Implementation of sha256 in WGSL
stablehlo - Backward compatible ML compute opset inspired by HLO/MHLO
numexpr - Fast numerical array expression evaluator for Python, NumPy, Pandas, PyTables and more
wgpu-py - Next generation GPU API for Python
graphics_wgpu
tfjs - A WebGL accelerated JavaScript library for training and deploying ML models.
vswhere - Locate Visual Studio 2017 and newer installations
webgpu-blas - Fast matrix-matrix multiplication on web browser using WebGPU
fastplotlib - Next-gen fast plotting library running on WGPU using the pygfx rendering engine
web-stable-diffusion - Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.
three.py - Python 3D library based on three.js and Modern OpenGL