Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
Ternative – C++/CUDA inference engine for ternary LLMs with runtime LoRA | Heykuki News
Ternative – C++/CUDA inference engine for ternary LLMs with runtime LoRA
github.com/michelangeloromerochisco
3 points
michelangeloro
18 days ago
1 comment
Loading...