llama.cpp
f142cfff
- Temp workaround for moe-cache with scaled data-types
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 days ago
Temp workaround for moe-cache with scaled data-types
References
#28898 - ggml: support quant scales for fp8 and nvfp4
#29791 - vulkan: add fp8 and scaled matmul support
Author
ORippler
Committer
ORippler
Parents
13ec5523
Loading