Georgi Gerganov e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)		10 月之前
..
CMakeLists.txt	7cc2d2c889 ggml : move AMX to the CPU backend (#10570)	1 年之前
README.md	532dd74e38 Fix some documentation typos/grammar mistakes (#4032)	2 年之前
parallel.cpp	e0dbec0bc6 llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)	10 月之前

llama.cpp/example/parallel

镜像来自 https://github.com/cturan/llama.cpp

Simplified simulation of serving incoming requests in parallel