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

Shorter dequantize_mul_mat_vec line

Browse source
This commit is contained in:
JohannesGaessler 2023-05-12 23:30:17 +02:00
parent f0af475739
commit 0986c2f44e
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml-cuda.cu
View file

@ -206,7 +206,8 @@ static __global__ void dequantize_block_q8_0(const void * vx, float * y) {
} }
} }
template <int block_size, int qk, dequantize_kernel_t dequantize_kernel> static __global__ void dequantize_mul_mat_vec(const void * vx, const float * y, float * dst, const int ncols) { template <int block_size, int qk, dequantize_kernel_t dequantize_kernel>
static __global__ void dequantize_mul_mat_vec(const void * vx, const float * y, float * dst, const int ncols) {
const int row = blockIdx.x; const int row = blockIdx.x;
const int tid = threadIdx.x; const int tid = threadIdx.x;