llama.cpp
b6fc9f03
- ggml-metal : supports_op returns false for ternary types
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
333 days ago
ggml-metal : supports_op returns false for ternary types Maybe not the cleanest way, but hopefully temporary.
References
#11183 - ggml-cuda : add TQ2_0 kernels, for ternary inference on GPU
Author
compilade
Committer
compilade
Parents
946796fc
Loading