mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-16 11:27:03 +00:00
6 lines
185 B
Plaintext
6 lines
185 B
Plaintext
#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);
|