llama.cpp
8a8c4ceb
- llamafile: use member variable instead of constant for iq4nlt (#11780)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
317 days ago
llamafile: use member variable instead of constant for iq4nlt (#11780)
References
#11780 - fix crash on non-AVX systems dynamically loading GGML CPU backends
Author
jmorganca
Parents
c1f958c0
Loading