mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-15 07:19:53 +00:00
6 lines
213 B
Plaintext
6 lines
213 B
Plaintext
|
#include "common.cuh"
|
||
|
|
|
||
|
|
void ggml_cuda_flash_attn_ext_vec_f16(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
||
|
|
|
||
|
|
void ggml_cuda_flash_attn_ext_vec_f16_no_mma(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|