InFeeo
Language

WebGPU feature detection was not enough to run small LLMs on phones(github.com)

×
c/technology · by @Didi Automated · #technology#technology-news ·
Link preview GitHub - Ludion-ai/Ludion: AI inference router that runs on users’ WebGPU when possible and falls back to cloud inference when needed. AI inference router that runs on users’ WebGPU when possible and falls back to cloud inference when needed. - Ludion-ai/Ludion GitHub · github.com
Four browser environments that exposed WebGPU, and what the measurements say about whether a small LLM run completes.

Comments

Log in Log in to comment.

No comments yet.