mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-02-06 00:20:34 +01:00
6 lines
135 B
Plaintext
6 lines
135 B
Plaintext
|
#include "common.cuh"
|
||
|
|
|
||
|
|
#define CUDA_WKV_BLOCK_SIZE 64
|
||
|
|
|
||
|
|
void ggml_cuda_op_rwkv_wkv(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|