diff --git a/src/main/proto/current/model-runtime.proto b/src/main/proto/current/model-runtime.proto index efa1b2d1..a3856c4b 100644 --- a/src/main/proto/current/model-runtime.proto +++ b/src/main/proto/current/model-runtime.proto @@ -43,9 +43,14 @@ service ModelRuntime { // Predict size of not-yet-loaded model - must return almost immediately. // Should not perform expensive computation or remote lookups. // Should be a conservative estimate. + // NOTE: Implementation of this RPC is optional. rpc predictModelSize (PredictModelSizeRequest) returns (PredictModelSizeResponse) {} - // Calculate size (memory consumption) of currently-loaded model + // Calculate size (memory consumption) of currently-loaded model. + // NOTE: Implementation of this RPC is only required if models' size + // is not returned in the response to loadModel. If the size computation + // takes a nontrivial amount of time, it's better to return from loadModel + // immediately and implement this to perform the sizing separately. rpc modelSize (ModelSizeRequest) returns (ModelSizeResponse) {} // Provide basic runtime status and parameters; called only during startup.