tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-26 03:03:25 -04:00
Code Issues Packages Projects Releases Wiki Activity

sync : ggml (#6351)

Browse Source 
* sync : ggml

ggml-ci

* cuda : move GGML_CUDA_DMMV constants to dmmv.cuh

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov
2024-03-29 17:45:46 +02:00
committed by GitHub
parent 069574775c
commit d48ccf3ad4
6 changed files with 25 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
ggml-cuda/dmmv.cuh
View File

@ -1,5 +1,16 @@
#include "common.cuh"
// dmmv = dequantize_mul_mat_vec
// TODO: remove this?
#ifndef GGML_CUDA_DMMV_X
#define GGML_CUDA_DMMV_X 32
#endif
#ifndef GGML_CUDA_MMV_Y
#define GGML_CUDA_MMV_Y 1
#endif
void ggml_cuda_op_dequantize_mul_mat_vec(
ggml_backend_cuda_context & ctx,
const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst, const char * src0_dd_i, const float * src1_ddf_i,