metal : fix failure to load model (ggerganov#1817)

The number of buffers in the ggml context was left unitialized. This leads to sporadic failures to load the model on startup. It is actually strange that the failure occurred so infrequantly. Co-authored-by: Iwan Kawrakow <[email protected]>
yxq321 · Jun 12, 2023 · 8c0a10e · 8c0a10e
1 parent fa84c4b
commit 8c0a10e
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/ggml-metal.m b/ggml-metal.m
@@ -86,6 +86,7 @@ @implementation GGMLMetalClass
 
     ctx->device = MTLCreateSystemDefaultDevice();
     ctx->queue  = [ctx->device newCommandQueue];
+    ctx->n_buffers = 0;
 
     // determine if we can use MPS
     if (MPSSupportsMTLDevice(ctx->device)) {