llama.cpp/docs/backend
Chenguang Li 28b5f190ef
CANN: implement LRU cache for ACL graphs (#15814)
* CANN: implement LRU cache for ACL graphs in CANN backend

- Introduce ggml_cann_graph_lru_cache to store multiple ggml_cann_graph objects.
- Graphs are loaded on demand and evicted using LRU policy when capacity is exceeded.
- Updated push, move_to_front, and clear methods to manage cached graphs efficiently.
- Ensures reuse of graphs, reducing graph reconstruction overhead in CANN backend.

* fix typo

* The LRU cache capacity can be configured via an env variable

Signed-off-by: noemotiovon <757486878@qq.com>

* refactory acl graph

* refactory && fix review comments

Signed-off-by: noemotiovon <757486878@qq.com>

---------

Signed-off-by: noemotiovon <757486878@qq.com>
2025-09-10 15:29:12 +08:00
..
BLIS.md make : deprecate (#10514) 2024-12-02 21:22:53 +02:00
CANN.md CANN: implement LRU cache for ACL graphs (#15814) 2025-09-10 15:29:12 +08:00
CUDA-FEDORA.md docs: update: improve the Fedoa CUDA guide (#12536) 2025-03-24 11:02:26 +00:00
OPENCL.md opencl: update doc for OpenCL (#12702) 2025-04-03 22:18:17 -07:00
SYCL.md sycl: GGML_SYCL_DISABLE_OPT on by default for all Intel Devices (#13973) 2025-06-25 18:09:55 +02:00