ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-30 11:21:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Do not use split mode graph scheduling if there are tensor overrides

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-12-12 13:36:02 +00:00
parent cc14d4a3cc
commit 082545b3f0
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama.cpp
View File

@@ -4771,7 +4771,7 @@ struct llama_context * llama_new_context_with_model(
LLAMA_LOG_INFO("XXXXXXXXXXXXXXXXXXXXX Setting only active experts offload\n"); LLAMA_LOG_INFO("XXXXXXXXXXXXXXXXXXXXX Setting only active experts offload\n");
ggml_backend_sched_set_only_active_experts(ctx->sched, true); ggml_backend_sched_set_only_active_experts(ctx->sched, true);
} }
if (model->split_mode == LLAMA_SPLIT_MODE_GRAPH) { if (model->split_mode == LLAMA_SPLIT_MODE_GRAPH && !model->has_tensor_overrides()) {
ggml_backend_sched_set_split_mode_graph(ctx->sched, true); ggml_backend_sched_set_split_mode_graph(ctx->sched, true);
} }