CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

cuda : refactor into multiple files (#6269)

Browse Source
This commit is contained in:
slaren
2024-03-25 13:50:23 +01:00
committed by GitHub
parent ad3a0505e3
commit ae1f211ce2
59 changed files with 9154 additions and 8987 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
ggml-cuda/quantize.cuh Normal file
View File

@@ -0,0 +1,5 @@
#include "common.cuh"
#define CUDA_QUANTIZE_BLOCK_SIZE 256
void quantize_row_q8_1_cuda(const float * x, void * vy, const int kx, const int ky, const int kx_padded, cudaStream_t stream);