vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

clear before resize

Browse source
This commit is contained in:
Alan Gray 2024-09-20 01:05:12 -07:00
parent c6b3ea6595
commit b51daccd6b
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ggml/src/ggml-cuda.cu
View file

@ -2700,10 +2700,10 @@ GGML_CALL static enum ggml_status ggml_backend_cuda_graph_compute(ggml_backend_t
// First call with null argument gets number of nodes in graph
CUDA_CHECK(cudaGraphGetNodes(cuda_ctx->cuda_graph->graph, nullptr, &cuda_ctx->cuda_graph->num_nodes));
// Subsequent call with non-null argument gets nodes
cuda_ctx->cuda_graph->nodes.resize(cuda_ctx->cuda_graph->num_nodes);
cuda_ctx->cuda_graph->nodes.clear();
cuda_ctx->cuda_graph->params.resize(cuda_ctx->cuda_graph->num_nodes);
cuda_ctx->cuda_graph->nodes.resize(cuda_ctx->cuda_graph->num_nodes);
cuda_ctx->cuda_graph->params.clear();
cuda_ctx->cuda_graph->params.resize(cuda_ctx->cuda_graph->num_nodes);
if (cuda_ctx->cuda_graph->num_nodes > 0) {
CUDA_CHECK(cudaGraphGetNodes(cuda_ctx->cuda_graph->graph, cuda_ctx->cuda_graph->nodes.data(), &cuda_ctx->cuda_graph->num_nodes));