cturan/llama.cpp

Mirror von https://github.com/cturan/llama.cpp

Autor	SHA1 Nachricht	Datum
Alfred	ce734a8a2f ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (#17977)	vor 4 Wochen
Max Krasnyansky	63d2fc46e1 Add experimental ggml-hexagon backend for the Hexagon NPU (#16547)	vor 2 Monaten