This paper develops a new series of large language models (Xing 4) by optimizing architecture and training infrastructure for efficient use on specialized chips (Ascend). Practitioners may care about the techniques described here because they could improve the performance and scalability of their own AI models.
Firehose
Filtered to Papers, tagged “Ascend chips” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives