cturan/llama.cpp

mirror da https://github.com/cturan/llama.cpp

Autore	SHA1 Messaggio	Data
Alfred	ce734a8a2f ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (#17977)	4 settimane fa
Max Krasnyansky	63d2fc46e1 Add experimental ggml-hexagon backend for the Hexagon NPU (#16547)	2 mesi fa