tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-08 01:26:51 -04:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: add mean operation (#14313)

Browse Source 
* CUDA: add mean operation

* add back sum_rows_f32_cuda

* Review: early exit if col!=0
This commit is contained in:
Aman Gupta
2025-06-22 12:39:54 +08:00
committed by GitHub
parent aa0ef5c578
commit aa064b2eb7
7 changed files with 54 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@@ -37,6 +37,7 @@
#include "ggml-cuda/ssm-scan.cuh"
#include "ggml-cuda/sum.cuh"
#include "ggml-cuda/sumrows.cuh"
#include "ggml-cuda/mean.cuh"
#include "ggml-cuda/tsembd.cuh"
#include "ggml-cuda/unary.cuh"
#include "ggml-cuda/upscale.cuh"
@@ -2357,6 +2358,9 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg
case GGML_OP_SUM_ROWS:
ggml_cuda_op_sum_rows(ctx, dst);
break;
case GGML_OP_MEAN:
ggml_cuda_op_mean(ctx, dst);
break;
case GGML_OP_SSM_CONV:
ggml_cuda_op_ssm_conv(ctx, dst);
break;
@@ -3260,6 +3264,7 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
case GGML_OP_POOL_2D:
case GGML_OP_SUM:
case GGML_OP_SUM_ROWS:
case GGML_OP_MEAN:
case GGML_OP_ARGSORT:
case GGML_OP_ACC:
return true;