deepspeedai--deepspeed/docs/_posts/2021-05-14-inference-release.md

title, date, link, excerpt, tags

title	date	link	excerpt	tags
DeepSpeed: Accelerating large-scale model inference and training via system optimizations and compression	2021-05-14	https://www.microsoft.com/en-us/research/blog/deepspeed-accelerating-large-scale-model-inference-and-training-via-system-optimizations-and-compression/		inference English