Bug DMLFusedNode_0_0 on second token in 0.5.2 (DML) (Wrong tensor shape)

Nobody has claimed this yet.

I updated to 0.5.2 DirectML mode. Quadro P5000 GPU. Windows. C# DirectML 1.15.4. Model: microsoft/Phi-3-mini-4k-instruct-onnx

I get the following bug. (Bug only comes up in DML mode not CPU mode. It worked in version 0.4.0).

For any prompt e.g.
"<|user|>Hello <|end|><|assistant|>"
(tokens:)
1,32010,15043,29871,32007,32001

It outputs one token but then when trying to output the second token it errors out with:

```
OnnxRuntimeGenAIException: Non-zero status code returned while running DmlFusedNode_0_0 node. Name:'DmlFusedNode_0_0' Status Message: D:\a\_work\1\s\onnxruntime\core\framework\execution_frame.cc:173 onnxruntime::IExecutionFrame::GetOrCreateNodeOutputMLValue shape && tensor.Shape() == *shape was false. OrtValue shape verification failed. Current shape:{1,32,7,96} Requested shape:{1,32,2048,96}

Microsoft.ML.OnnxRuntimeGenAI.Result.VerifySuccess (System.IntPtr nativeResult) (at D:/a/_work/1/onnxruntime-genai/src/csharp/Result.cs:25)
Microsoft.ML.OnnxRuntimeGenAI.Generator.ComputeLogits () (at D:/a/_work/1/onnxruntime-genai/src/csharp/Generator.cs:25)
Main.Generate () (at Assets/Main.cs:202)
```

The relevant part seems to be: Current shape:{1,32,**7**,96} Requested shape:{1,32,**2048**,96}

It appears to be not padding the tokens to the max_tokens or something.

Reproduce the second-token failure with the Phi-3-mini-4k-instruct-onnx model in DirectML mode, then compare it with CPU mode and version 0.4.0. Start from the generation path shown in Assets/Main.cs:202 and Microsoft.ML.OnnxRuntimeGenAI/Generator.cs:25; done means the prompt generates past the second token without the DmlFusedNode shape mismatch.

Written by the indexing model from the issue text.