Team Ai
Apppublic

KBaba7/llama.cpp

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes
rootllama.cppggmlsrcggml-cudascale.cuh
scale.cuh6 linesDownload Raw Back to ggml-cuda
1#include "common.cuh"2 3#define CUDA_SCALE_BLOCK_SIZE 2564 5void ggml_cuda_op_scale(ggml_backend_cuda_context & ctx, ggml_tensor * dst);6