Georgi Gerganov a10b36c91a llama : refactor kv cache guard (#12695) 9 месяцев назад
..
CMakeLists.txt 7cc2d2c889 ggml : move AMX to the CPU backend (#10570) 1 год назад
README.md 532dd74e38 Fix some documentation typos/grammar mistakes (#4032) 2 лет назад
parallel.cpp a10b36c91a llama : refactor kv cache guard (#12695) 9 месяцев назад

README.md

llama.cpp/example/parallel

Simplified simulation of serving incoming requests in parallel