CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-08 10:07:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-zdnn: tighten memory usage, change string allocation

Browse Source 
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
Aaron Teo
2025-07-28 15:55:42 +08:00
parent aef93b3908
commit bee7dd3020
2 changed files with 3 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-zdnn/ggml-zdnn-impl.h
View File

@@ -59,13 +59,13 @@ typedef unsigned long long ulong64x2_t __attribute__((vector_size(16)));
struct ggml_backend_zdnn_buffer {
void * data;
size_t size;
ggml_backend_zdnn_buffer * extra; // for bias etc.
zdnn_tensor_desc pre_tfm_desc;
zdnn_tensor_desc tfm_desc;
zdnn_ztensor ztensor;
char name[GGML_MAX_NAME];
struct ggml_backend_zdnn_buffer * extra; // for bias etc.
ggml_backend_zdnn_buffer() : extra(nullptr) {}
};