mms
mms copied to clipboard
Published
20 hours ago •
alpa-projects
alpa-projects
AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)
AlpaServe
Repo of alpa's multi-model serving system.
This is the official implementation of our OSDI'23 paper: AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving.
To reproduce all the main results in our paper, please check the artifact folder and follow the instructions in it.
Metadata
60
Stars
9
Forks
Watchers
Owner
alpa-projects
Metadata
AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)