llama.cpp
983aa09b
- Merge branch 'master' into compilade/cuda-tq2_0
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
303 days ago
Merge branch 'master' into compilade/cuda-tq2_0
References
#11183 - ggml-cuda : add TQ2_0 kernels, for ternary inference on GPU
Author
compilade
Parents
fb43d5e8
1204f972
Loading
