ggml-org/llama.cpp b8846

on GitHub

ggml : reduce CPU overhead in meta backend (#22041)

• cache subgraph splits when cgraph is unchanged

Skip per-call subgraph construction in ggml_backend_meta_graph_compute when the same ggml_cgraph is used consecutively.

Assign uid to every sub-graph so that CUDA's fast uid check path hits too.

• Address review comments

• Keep the scope as is

• Rename last_uid and last_n_subgraphs field. Remove last_max_tmp_size field. Refactor code.

• Address review comments

• Update ggml/src/ggml-backend-meta.cpp

Co-authored-by: Johannes Gäßler johannesg@5d6.de

• Update ggml/src/ggml-backend-meta.cpp

Co-authored-by: Johannes Gäßler johannesg@5d6.de

Co-authored-by: Johannes Gäßler johannesg@5d6.de