Gaurav GargandJohannes Gäßler 671fd1527a ggml : reduce CPU overhead in meta backend (llama/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>

2026-04-30 11:29:13 +03:00

..

cmake

cmake : remove unused file (ggml/1419)

2026-02-08 09:29:10 +02:00

include

CUDA: manage NCCL communicators in context (llama/21891)

2026-04-30 11:29:09 +03:00

src

ggml : reduce CPU overhead in meta backend (llama/22041)

2026-04-30 11:29:13 +03:00

.gitignore

whisper : reorganize source code + improve CMake (#2256)

2024-06-26 19:34:09 +03:00

CMakeLists.txt

cmake: remove CMP0194 policy to restore MSVC builds (llama/21934)

2026-04-30 11:29:12 +03:00