llama.cpp
a462159c
- cuda : ggml_cuda_op_mul_mat_cublas support F32 precision
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
cuda : ggml_cuda_op_mul_mat_cublas support F32 precision
References
gg/phi-2-2
Author
ggerganov
Parents
30338c56
Loading