llama.cpp
ggml : add aarch64 HWCAP fallbacks and fix fp16 variant detection
#25554
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
2
Changes
View On
GitHub
Commits
ggml : add fallback definitions for missing aarch64 HWCAP bits
kilian-hu
committed
11 days ago
ggml : require HWCAP_ASIMDHP for the aarch64 fp16 cpu variants
kilian-hu
committed
11 days ago
Loading