Hugging Face releases WebGPU kernel library and 207 kernels
Understand this story
Hugging Face's WebAI team has released the JavaScript library @huggingface/kernels, used to load and run optimized WebGPU kernels from the Hugging Face Hub, and has also launched 207 kernel repositories released under the Apache-2.0 license. The library must be installed from npm as a preview version (npm install @huggingface/kernels@preview), and running the kernels requires browser support for WebGPU. Hugging Face says that, with user consent, each run adds private evidence used to detect incorrect results, unusual slowness, and other issues, and to improve kernel variants and make optimization decisions on real hardware.
AI overview based on source reports · Updated 3 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIHuggingFace/Kernels: 200 WebGPU Kernels for Local AI
Hugging Face released @huggingface/kernels, a minimal JavaScript library for loading and running optimized WebGPU kernels from the Hugging Face Hub, alongside an initial collection of 207 Apache-2.0 licensed kernels at huggingface.co/webgpu-kernels. Each kernel is published as a versioned repository containing a manifest, correctness and benchmark cases, and parameterized WGSL shader templates, and the team also launched Fleet, an in-browser GPU benchmarking suite that crowdsources correctness and performance evidence. In comparisons against ONNX Runtime WebGPU on an Apple M4 GPU across 809 matching cases, the kernels were 2.57x faster by geometric mean and 1.90x faster at the median.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 12 07:00
- Change in the past 24 hours
- -50%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.