CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fixes after sync (ggml/983)

Browse Source 
ggml : remove test-backend-buffer

ggml : fix CUDA build warnings
This commit is contained in:
Diego Devesa
2024-10-04 08:41:40 +02:00
committed by Georgi Gerganov
parent f3fdcfaa79
commit ff565769f2
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda.cu
View File

@@ -2448,6 +2448,7 @@ static void ggml_backend_cuda_synchronize(ggml_backend_t backend) {
GGML_UNUSED(backend);
}
#ifdef USE_CUDA_GRAPH
static void set_ggml_graph_node_properties(ggml_tensor * node, ggml_graph_node_properties * graph_node_properties) {
graph_node_properties->node_address = node->data;
graph_node_properties->node_op = node->op;
@@ -2498,6 +2499,7 @@ static bool ggml_graph_node_has_matching_properties(ggml_tensor * node, ggml_gra
return true;
}
#endif
static enum ggml_status ggml_backend_cuda_graph_compute(ggml_backend_t backend, ggml_cgraph * cgraph) {
ggml_backend_cuda_context * cuda_ctx = (ggml_backend_cuda_context *)backend->context;