microsoft/DeepSpeed-MII
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
PythonApache-2.0
Stargazers
- bzantiumKakaobrain
- Categorytyy
- chrjxjnvidia
- Codle@bytedance
- deekshakoul
- eagle705SKTelecom
- eubinecto@WRTN-Technologies
- fly51flyPRIS
- GeraldCSCToronto, Canada
- Gforky
- hungnphan@caddijp
- hyunwoongko@kakao
- jeffra@snowflakedb
- jeonsworld@kakaobank
- jinyongyooHyperconnect
- jl749
- l-yohai@coxwave
- LeeDoYupRunway
- lipovsekAWS
- michalwolsNew York
- monologg@bhsn-ai
- nateraw@huggingface
- nikitavoloboevMadrid
- philschmid@huggingface
- prateekralhan@SwissRe
- RiccorlPhD @SapienzaNLP
- ryantd@kwai
- samyam
- saranshkarira
- shpotesGoogle
- snoop2headKAIST AI
- stas00Stasosphere Online Inc. / Contextual.AI
- troyyyang
- upskyyReturnZero Inc.
- VegeWong
- wavy-jung@kakao