CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-01 09:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

allocator: fix partial offloading

Browse Source
This commit is contained in:
slaren
2023-07-22 01:46:49 +02:00
parent e87840f9fd
commit 7de7882537
3 changed files with 82 additions and 137 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml-backend.h
View File

@@ -155,7 +155,6 @@ extern "C" {
// graph tensor allocator
GGML_API void ggml_graph_allocate_tensors(struct ggml_cgraph * graph, struct ggml_context * ctx);
GGML_API void ggml_graph_allocate_tensors_n(struct ggml_cgraph ** graphs, int n_graphs, struct ggml_context * ctx);
GGML_API void ggml_graph_splits_allocate_tensors(struct ggml_graph_splits * splits);
#ifdef __cplusplus