ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

cuBLAS: non-contiguous tensor support (#1215)

Browse source 
* Cuda: non-contiguous tensor support

* remove extra stuff

* rename

* fix error

* more fixes, now OpenBLAS and CLBlast build too

* now then?
This commit is contained in:
Henri Vasserman 2023-04-29 02:31:56 +03:00 • committed by GitHub
parent 36d19a603b
commit b1ee8f59b4
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 44 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml-cuda.h
View file

@ -1,5 +1,6 @@
#include <cublas_v2.h>
#include <cuda_runtime.h>
#include "ggml.h"
#ifdef __cplusplus
extern "C" {
@ -38,6 +39,8 @@ void dequantize_row_q5_0_cuda(const void * vx, float * y, int k, cudaStream_t st
void dequantize_row_q5_1_cuda(const void * vx, float * y, int k, cudaStream_t stream);
void dequantize_row_q8_0_cuda(const void * vx, float * y, int k, cudaStream_t stream);
cudaError_t ggml_cuda_h2d_tensor_2d(void * dst, const struct ggml_tensor * src, uint64_t i3, uint64_t i2, cudaStream_t stream);
#ifdef __cplusplus
}
#endif