Add int8 quantized models (EnableSubgraph: True)

- encoder_model_quantized.onnx: 136 MB -> 34 MB (75% reduction)
- decoder_model_merged_quantized.onnx: 160 MB -> 41 MB (74% reduction)
- Total: 297 MB -> 77 MB (74% reduction)

Quantized with onnxruntime.quantization.quantize_dynamic + EnableSubgraph=True
to traverse the If-node subgraphs in the merged decoder.

decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b3b8ba87448d36175951f5d06062b3ec2220119ec122a21b5b93dd77642fb68
+size 42973585

encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975b073a1b71017175c8d4f70f36d4105b118d60018897c501c9808cc297bafc
+size 35865699