Aman GuptaandGitHub
a90eb94ca9
* CUDA: add fused rope * move k forward_expand up * create helper function instead of re-using params * make assert statement more in line with comment * rope_norm: coalesced writes to global mem
10 lines
322 B
Plaintext
10 lines
322 B
Plaintext
#include "common.cuh"
|
|
|
|
#define CUDA_ROPE_BLOCK_SIZE 256
|
|
|
|
void ggml_cuda_op_rope(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_rope_back(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
|
|
|
|
void ggml_cuda_op_rope_fused(ggml_backend_cuda_context & ctx, ggml_tensor * dst, ggml_tensor * set_rows);
|