upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-03 00:20:50 -05:00
Code Issues Packages Projects Releases Wiki Activity
Files
2c3ed6086f470b8816158bd90ac0938ff7fcbf90
llama.cpp/tools/server/server-context.cpp
Georgi Gerganov 2c3ed6086f server : add trace logs for slot prefix similarity computation 
Log the computed prefix similarity values for each slot during slot
selection, including the common prefix length, task token count,
current similarity, best similarity so far, and the threshold.

Assisted-by: pi:llama.cpp/Qwen3.6-27B
2026-07-17 13:01:28 +03:00

213 KiB
Raw Blame History

View Raw
Reference in New Issue View Git Blame Copy Permalink