llama.cpp
4eb19514
- kv-cache : support attention rotation for heterogeneous iSWA (#21513)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
3 days ago
kv-cache : support attention rotation for heterogeneous iSWA (#21513) * kv-cache : support attention rotation for heterogeneous iSWA * cont : remove assert
References
#21513 - kv-cache : support attention rotation for heterogeneous iSWA
Author
ggerganov
Parents
957d717c
Loading