llama.cpp
vulkan: add TQ2_0 (ternary) support
#25850
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
2
Changes
View On
GitHub
Commits
vulkan: TQ2_0 (ternary) support — dequant + dedicated mul_mat_vec + matmul via dequant_funcs
Michael Trabalka
committed
30 days ago
tests: enable TQ2_0 in backend-ops type lists
Michael Trabalka
committed
30 days ago
Loading
