ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-28 10:21:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

Command line option to set max. extra VRAM that the scheduler can use

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-12-16 06:35:06 +00:00
parent 5235c8b3e4
commit ec2ba592b5
6 changed files with 24 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/include/ggml-backend.h
View File

@@ -212,6 +212,7 @@ extern "C" {
GGML_API void ggml_backend_sched_set_op_offload(ggml_backend_sched_t sched, enum ggml_op op, bool on_or_off);
GGML_API void ggml_backend_sched_set_only_active_experts(ggml_backend_sched_t sched, bool on_or_off);
GGML_API void ggml_backend_sched_set_split_mode_graph(ggml_backend_sched_t sched, bool on_or_off);
GGML_API void ggml_backend_sched_set_max_extra_alloc(ggml_backend_sched_t sched, int extra_alloc_MiB);
//
// Utils