Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI [LAB]
Provides low-level WebGPU kernels to enable high-performance local inference directly in the browser. https://huggingface.co/blog/webgpu-kernels (huggingface.co)
[2507.21504] Evaluation and Benchmarking of LLM Agents: A Survey [web]
A comprehensive survey on the methodologies and metrics required to evaluate agentic workflows and tool use. https://arxiv.org/abs/2507.21504 (arxiv.org)