CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : use autoreleasepool to avoid memory leaks (#5437)

Browse Source 
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
This commit is contained in:
Ian Bull
2024-02-10 02:53:28 -08:00
committed by GitHub
parent cd9aea63b5
commit f026f8120f
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml-metal.m
View File

@@ -687,6 +687,7 @@ static bool ggml_metal_graph_compute(
struct ggml_metal_context * ctx, struct ggml_metal_context * ctx,
struct ggml_cgraph * gf) { struct ggml_cgraph * gf) {
@autoreleasepool {
MTLComputePassDescriptor * edesc = MTLComputePassDescriptor.computePassDescriptor; MTLComputePassDescriptor * edesc = MTLComputePassDescriptor.computePassDescriptor;
edesc.dispatchType = MTLDispatchTypeSerial; edesc.dispatchType = MTLDispatchTypeSerial;
@@ -2272,6 +2273,7 @@ static bool ggml_metal_graph_compute(
[[MTLCaptureManager sharedCaptureManager] stopCapture]; [[MTLCaptureManager sharedCaptureManager] stopCapture];
} }
}
return true; return true;
} }