mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-09-23 05:26:19 +00:00
4 lines
114 B
Plaintext
4 lines
114 B
Plaintext
|
#include "common.cuh"
|
||
|
|
|
||
|
|
void ggml_cuda_flash_attn_ext_vec_f32(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|