llama.cpp/docs
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
..
backend CANN: implement LRU cache for ACL graphs (#15814) 2025-09-10 15:29:12 +08:00
development docs : update HOWTO‑add‑model.md for ModelBase and new model classes (#14874) 2025-07-25 16:25:05 +02:00
multimodal model : support MiniCPM-V 4.5 (#15575) 2025-08-26 10:05:55 +02:00
ops ggml: initial IBM zDNN backend (#14975) 2025-08-15 21:11:22 +08:00
android.md repo : update links to new url (#11886) 2025-02-15 16:40:57 +02:00
build-s390x.md ggml-cpu: drop support for nnpa intrinsics (#15821) 2025-09-06 11:27:28 +08:00
build.md Update build.md to remove MSVC arm64 notes (#15684) 2025-08-30 23:51:28 +08:00
docker.md musa: upgrade musa sdk to rc4.2.0 (#14498) 2025-07-24 20:05:37 +01:00
function-calling.md server : add documentation for `parallel_tool_calls` param (#15647) 2025-08-29 20:25:40 +03:00
install.md docs : add "Quick start" section for new users (#13862) 2025-06-03 13:09:36 +02:00
llguidance.md llguidance build fixes for Windows (#11664) 2025-02-14 12:46:08 -08:00
multimodal.md mtmd : add support for Voxtral (#14862) 2025-07-28 15:01:48 +02:00
ops.md ggml: initial IBM zDNN backend (#14975) 2025-08-15 21:11:22 +08:00