WebGPU in Chrome Canary now supports float16 for faster local LLM inference (twitter.com) 18 points by NiekvdMaas 2y ago ↗ HN
[–] NiekvdMaas 2y ago ↗ To test, run Chrome Canary with: --enable-dawn-features=allow_unsafe_apis,disable_robustness Then, open: https://webllm.mlc.ai/#chat-demo [–] hardware2win 2y ago ↗ >disable_robustnessWhat a name, especially since it improves perf
[–] no_time 2y ago ↗ I hope they gate webGPU behind a per domain allow/deny notification like they do with location and camera access.This whole thing is just begging to be exploited by cryptominers. [–] charcircuit 2y ago ↗ It may be more profitable to use the compute for LLMs or other GPU dependent AI than crypto mining. The downside is that there is no way to verify the client isn't returning random or bad data. [–] lostmsu 2y ago ↗ Cryptomining is mostly gone.
[–] charcircuit 2y ago ↗ It may be more profitable to use the compute for LLMs or other GPU dependent AI than crypto mining. The downside is that there is no way to verify the client isn't returning random or bad data.
5 comments
[ 2.2 ms ] story [ 35.0 ms ] threadWhat a name, especially since it improves perf
This whole thing is just begging to be exploited by cryptominers.