[WebNN EP] Cache MLTensors between runs (#22278)

### Description
This change enables caching `MLTensor`s between inferences runs. This is
done by keeping a reference to `MLTensor`s alive after they have been
released. `MLTensor`s are only destroyed once the sessions goes out of
scope.

### Motivation and Context
Creating and destroying `MTensor`s on every run has a non-trivial
performance penalty. This performance penalty materializes when using
`ort.Tensors`[location=cpu] for inputs/outputs or when using the CPU EP
as a fallback EP for unsupported operators. The former could be
mitigated by developer using `ort.Tensors`[location=ml-tensor]. The
latter cannot be mitigated by developers.

js/web/lib/wasm/jsep/backend-webnn.ts

@@ -91,12 +91,12 @@ export class WebNNBackend {
       // Current session is not a WebNN session.
       return;
     }
+    this.tensorManager.releaseTensorsForSession(sessionId);
     this.mlContextBySessionId.delete(sessionId);
     const sessionIds = this.sessionIdsByMLContext.get(mlContext)!;
     sessionIds.delete(sessionId);
     if (sessionIds.size === 0) {
       this.sessionIdsByMLContext.delete(mlContext);
-      this.tensorManager.releaseTensorsForContext(mlContext);
     }
   }