Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

metal: fix memory unwire if model is freed without any GPU operations (#26082)

Browse Source 
* metal: fix memory leak if model is freed without any GPU operations

* metal: run dummy work only if residency sets are used

* metal: wrap function in #if defined

* metal: measure system-wide wired memory in test

* metal: always build regression test

Co-authored-by: YiChen Lv <63285796+forforever73@users.noreply.github.com>

---------

Co-authored-by: YiChen Lv <63285796+forforever73@users.noreply.github.com>
This commit is contained in:
Niklas Wenzel
2026-07-30 11:11:27 +03:00
committed by GitHub
co-authored by YiChen Lv
parent 21a5f5b7f9
commit d0bfb19812
4 changed files with 94 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/CMakeLists.txt
+3
View File
@@ -278,6 +278,9 @@ set_tests_properties(test-state-restore-fragmented PROPERTIES FIXTURES_REQUIRED
llama_build_and_test(test-save-load-state.cpp LABEL "model" ARGS -m "${MODEL_DEST}")
set_tests_properties(test-save-load-state PROPERTIES FIXTURES_REQUIRED test-download-model)
if (APPLE)
llama_build(test-rset-release.cpp get-model.cpp)
endif()
if (NOT GGML_BACKEND_DL)
# these tests use the backends directly and cannot be built with dynamic loading
llama_build_and_test(test-barrier.cpp)