cturan/llama.cpp @ 2bed4aa3f37cb4e39e16e9ec7b595a7738fd5faf

kopia lustrzana https://github.com/cturan/llama.cpp

Georgi Gerganov bcc0eb4591 llama : per-layer KV cache + quantum K cache (#4309)		2 lat temu
..
CMakeLists.txt	b12fa0d1c1 build : link against build info instead of compiling against it (#3879)	2 lat temu
quantize-stats.cpp	bcc0eb4591 llama : per-layer KV cache + quantum K cache (#4309)	2 lat temu