Georgi Gerganov 6b0a7420d0 llama : KV cache view API + better KV cache management (#4170)		преди 2 години
..
CMakeLists.txt	b12fa0d1c1 build : link against build info instead of compiling against it (#3879)	преди 2 години
README.md	532dd74e38 Fix some documentation typos/grammar mistakes (#4032)	преди 2 години
parallel.cpp	6b0a7420d0 llama : KV cache view API + better KV cache management (#4170)	преди 2 години

llama.cpp/example/parallel

огледало от https://github.com/cturan/llama.cpp

Simplified simulation of serving incoming requests in parallel