ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-13 07:20:15 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
0369d2ba448941d216c5b35560745fde9d68f0eb
ik_llama.cpp/examples/server/utils.hpp
firecoperana 2cbfd04d88 Server: Handle context shift better to reduce prompt processing time (#973) 
* Handle context shift better to reduce pp

Add context-shift args

Add back ga_n in context shift

* optimize discard function and bring back n_keep = -1

---------

Co-authored-by: firecoperana <firecoperana>
2025-11-19 16:04:48 +01:00

54 KiB
Raw Blame History

View Raw
Reference in New Issue View Git Blame Copy Permalink