Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
PowerInfer: High-Speed Large Language Model Serving on Consumer-Grade GPUs
github.com/SJTU-IPADS
4 points
limoce
2 years ago
1 comment
Loading...
PowerInfer: High-Speed Large Language Model Serving on Consumer-Grade GPUs | Heykuki News