Hugging Face officially released Transformers.js v4, featuring a completely rewritten C++-based WebGPU runtime. Developed in close collaboration with the ONNX Runtime team, this update significantly improves performance, accuracy, and coverage for approximately 200 supported model architectures, marking a major leap in browser-side inference capabilities.
Termsslug: onnx-runtime
ONNX Runtime
Microsoft's cross-platform machine learning model accelerator
Curated Intelligence
Hugging Face BlogT1·Tools
78 pts
Hugging Face BlogT1·Tools
45 pts
Microsoft announced that ONNX Runtime now supports accelerating over 130,000 Hugging Face models. This integration aims to boost deployment efficiency and performance for open-source models via a standardized inference engine.
Hugging Face BlogT1·Tools
25 pts
Hugging Face Optimum announced deep integration with ONNX Runtime to simplify and accelerate model training workflows. The update focuses on developer experience and engine compatibility, lacking specific performance benchmarks or algorithmic breakthroughs.