From: Ian Bull <redacted>
Date: Sat, 10 Feb 2024 10:53:28 +0000 (-0800)
Subject: metal : use autoreleasepool to avoid memory leaks (llama/5437)
X-Git-Tag: upstream/0.0.1642~972
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=04b3bf5ddb49a3de311a1066599a3d1f7e9d5085;p=pkg%2Fggml%2Fsources%2Fggml

metal : use autoreleasepool to avoid memory leaks (llama/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
---

diff --git a/src/ggml-metal.m b/src/ggml-metal.m
index 5260ed82..c1d8e2de 100644
--- a/src/ggml-metal.m
+++ b/src/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;
 }