ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-26 17:20:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Disable split scheduling with tensor overrides

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-12-17 06:38:18 +00:00
parent 7a7029ec99
commit 0864655a72
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

@@ -4773,7 +4773,7 @@ struct llama_context * llama_new_context_with_model(
LLAMA_LOG_INFO("XXXXXXXXXXXXXXXXXXXXX Setting only active experts offload\n");
ggml_backend_sched_set_only_active_experts(ctx->sched, true);
}
if (model->split_mode == LLAMA_SPLIT_MODE_GRAPH) { // && !model->has_tensor_overrides()) {
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_max_extra_alloc(ctx->sched, params.max_extra_alloc);
}