llama-cpp-sys-4 0.3.1

Low Level Bindings to llama.cpp
Documentation 
1
2
3
4
5
6
7

#include "common.cuh"

void ggml_cuda_flash_attn_ext(ggml_backend_cuda_context & ctx, ggml_tensor * dst);

bool ggml_cuda_flash_attn_ext_supported(int device, const ggml_tensor * dst);

size_t ggml_cuda_flash_attn_ext_get_alloc_size(int device, const ggml_tensor * dst);