llama.cpp
2f3fd025
- Enable CUDA graph for MTP draft (#28549)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
53 days ago
Enable CUDA graph for MTP draft (#28549) * Improve CUDA graph usage for MTP * Rename field * Address review feedback
References
#28549 - Enable CUDA graph for MTP draft
Author
gaugarg-nv
Parents
1ec81880
Loading