CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-12 10:47:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal: optimise GGML_OP_SUM (#16559)

Browse Source 
* optimise GGML_OP_SUM

* add non-contiguous tests by permuting the input

* change tests to require full contiguity of OP_SUM

* cuda : add check GGML_OP_SUM

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Sam/Samuel
2025-10-15 23:05:56 +09:00
committed by GitHub
parent 17304cbcc1
commit f4ce81c45e
5 changed files with 71 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@@ -3625,9 +3625,10 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
case GGML_OP_CONV_2D_DW:
case GGML_OP_CONV_TRANSPOSE_2D:
case GGML_OP_POOL_2D:
case GGML_OP_SUM:
case GGML_OP_ACC:
return true;
case GGML_OP_SUM:
return ggml_is_contiguous_rows(op->src[0]);
case GGML_OP_ARGSORT:
// TODO: Support arbitrary column width
return op->src[0]->ne[0] <= 1024;