From f026f8120f97090d34a52b3dc023c82e0ede3f7d Mon Sep 17 00:00:00 2001 From: Ian Bull Date: Sat, 10 Feb 2024 02:53:28 -0800 Subject: [PATCH] metal : use autoreleasepool to avoid memory leaks (#5437) There appears to be a known memory leak when using the `MLTCommandBuffer`. It is suggested to use `@autoreleasepool` in [1,2] [1] https://developer.apple.com/forums/thread/662721 [2] https://forums.developer.apple.com/forums/thread/120931 This change-set wraps the `ggml_metal_graph_compute` in a `@autoreleasepool`. This commit addresses https://github.com/ggerganov/llama.cpp/issues/5436 --- ggml-metal.m | 2 ++ 1 file changed, 2 insertions(+) diff --git a/ggml-metal.m b/ggml-metal.m index 5260ed827..c1d8e2de8 100644 --- a/ggml-metal.m +++ b/ggml-metal.m @@ -687,6 +687,7 @@ static bool ggml_metal_graph_compute( struct ggml_metal_context * ctx, struct ggml_cgraph * gf) { + @autoreleasepool { MTLComputePassDescriptor * edesc = MTLComputePassDescriptor.computePassDescriptor; edesc.dispatchType = MTLDispatchTypeSerial; @@ -2272,6 +2273,7 @@ static bool ggml_metal_graph_compute( [[MTLCaptureManager sharedCaptureManager] stopCapture]; } + } return true; }