原推：Efficiently offloading the model into lower cost memory also reduces cost per token.
Sure, it’s not as fast as cloud-inferring on $200k worth of GPUs, but it reduces cost per token generated by 75%
翻译英文优质信息和名人推特
原推：Efficiently offloading the model into lower cost memory also reduces cost per token.
Sure, it’s not as fast as cloud-inferring on $200k worth of GPUs, but it reduces cost per token generated by 75%