llama.cpp
4d719a6d
- cuda : check if this fixes Pascal card regression (#3882)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Hide Minimap (CTRL+M)
Commit
1 year ago
cuda : check if this fixes Pascal card regression (#3882)
References
#3882 - cuda : do not use batched GEMM when tensor cores are not available
Author
ggerganov
Parents
183b3fac
Files
1
ggml-cuda.cu
Loading