AI-Hypercomputer/JetStream
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
PythonApache-2.0
Stargazers
- adarshxsTensoic AI
- akashsonowalMphasis Limited
- alanwaketanGoogle LLC
- anagriBangalore
- aruethGoogle
- bivens-dev
- borisdayma
- CatherineF-dev@google
- ChenghaoMouDocusign
- Davidnet@updata-ca
- DavidPeleg6
- dhruvrnaikCurai Health
- dkashkinGoogle
- entrpnGoogle
- evdcush
- girishramnaniIndia
- honglu2875Switzerland
- hyoshida123Tokyo, Japan
- joennlaeETH Zürich
- JoeZijunZhou
- kathir-ks
- leiterenatoWorld
- liurupengGoogle
- patemotterGoogle
- Rohith04MVK@Deep-Alchemy
- rudeigercWizardQuant
- saitej123Bangalore
- SandalotsVolcanak
- Sea-SnellBerkeley, CA
- sharadmvGoogle
- shauheenGoogle
- sozercan@Microsoft
- tensorboyTikTok Inc
- yarri-ossGoogle
- young-gengGoogle DeepMind
- ZhiHanZ