llama.cpp/include
Daniel Bevenius 61ffe41dc1
sampling : use pinned memory for backend sampling buffers
2025-11-21 14:02:16 +01:00
..
llama-cpp.h llama : add `llama_vocab`, functions -> methods, naming (#11110) 2025-01-12 11:32:42 +02:00
llama.h sampling : use pinned memory for backend sampling buffers 2025-11-21 14:02:16 +01:00