ollamarunner: Memory usage reporting

This provides granular information about the backend memory allocations
required by the runner:
 - Per backend
 - Per layer
 - Weights, cache and graph
 - Allocation status

This can be used for debugging and validating memory estimates.

runner/ollamarunner/multimodal.go

@@ -95,10 +95,7 @@ func (m multimodalStore) getTensor(backend ml.Backend, ctx ml.Context, in ml.Ten
 				}
 			}
 		} else {
-			err := computeCtx.Reserve()
-			if err != nil {
-				return nil, err
-			}
+			computeCtx.Reserve()
 		}
 	}