Fabrice Bellard: Fast, Standalone CPU Inference for Transformer Language Models | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Fabrice Bellard: Fast, Standalone CPU Inference for Transformer Language Models (bellard.org)
		7 points by 37ef_ced3 on July 14, 2021 \| hide \| past \| favorite \| 1 comment

h2odragon on July 15, 2021 [–]

also see https://bellard.org/nncp/ Lossless Data Compression with Neural Networks; which appears to be the immediate prompt.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact