DeepX claims inference up to 100B parameters at less than 5 W
DeepX's claim of performing inference for large language models with very low power consumption.
Hacker News submitter: giuliomagnifico
Submitted to Hacker News:
DeepX's claim of performing inference for large language models with very low power consumption.
Hacker News submitter: giuliomagnifico
Submitted to Hacker News: