G Gimlet Labs Blog company blog

Speeding up PyTorch inference on Apple devices with AI-generated Metal kernels

by Taras Sereda gimletlabs.ai published 2025-08-26

Our lab investigated whether frontier models can write optimized GPU kernels for Apple devices to speed up inference. We found that they can: our AI-generated Metal kernels were 1.24x faster across KernelBench v0.1 problems, and 1.87x faster across KernelBench v0 problems.

Points

187

HN comments

30

Submissions

1

Cited by

0 commenters

AI & Machine LearningSoftware Engineering2025

Related posts from the same era

Statement on US government directive to suspend access to Fable 5 and Mythos 5

Anthropic20263,158 points2,314 commentscited by 11 details

GPT-4o

OpenAI Blog20243,138 points2,366 commentscited by 16 details

Astra can read and write weights to improve Qwen

RRikiya Takehi20262,959 points899 comments details

HackerTube: YouTube built from videos recommended by HN

karpathy20262,886 points641 comments details

Claude Fable 5

Anthropic20262,626 points2,159 commentscited by 10 details

Claude Code is steganographically marking requests

Thereallo20262,445 points750 commentscited by 3 details