Myelin "Could not infer output types for operation: dequantize" on SM 8.7 (Orin); identical engine builds on SM 11.0 (Thor) with the same TensorRT 10.16.2.10

Summary

Myelin fails to compile a dequantize operation on SM 8.7 (Orin) that compiles successfully on SM 11.0 (Thor), with identical TensorRT 10.16.2.10, identical L4T R39.2, and the byte-identical ONNX file. The two devices differ only in GPU architecture.

Environment

Producer: NVIDIA ModelOpt 0.44.0 (modelopt.onnx.quantization), INT8 PTQ, entropy calibration, 320 real-image samples. Consumer: trtexec --stronglyTyped.

Reproduction

trtexec --onnx=quantized_int8.onnx --saveEngine=int8.engine --stronglyTyped

Failure

Every tactic is skipped with:

Error Code 9: ... [type.cpp:186: infer_type] Could not infer output types for operation:
291: dequantize: Dequantized input0-(f32[1,16,512,512]) | input0 reshape out_transpose_out
reshape out slice_U28 out-(i8[]), MyelinPW(42188) - Input Dequantization 0 scale
weightsHalf-0.35498H:(f16[]) ... No matching rules found for input operand types
In compileGraph at .../myelin/codeGenerator.cpp:1795

The operand mix is f32 activation + i8 slice + f16 scale. The Ampere codegen path appears to have no rule for that combination; the Blackwell path does.

What this is not

Three different quantization scopes were produced, giving three distinct artifacts. All three fail on Orin with a byte-identical error — same node 291, same MyelinPW(42188), same 0.35498 scale:

The error not moving while the graph does rules out quantization scope as the cause, and Thor compiling the identical file rules out the model and the calibration. That leaves architecture-specific codegen.

Impact

Strongly-typed INT8 is unavailable on Orin for this detector family. The documented alternative — weakly-typed --int8 --fp16 — permits silent downcast, which our deployment contract forbids.

Start by reproducing the failure with trtexec --onnx=quantized_int8.onnx --saveEngine=int8.engine --stronglyTyped on Orin, then compare the same artifact on Thor. Inspect the type inference location in type.cpp:186 and the code-generation path referenced at myelin/codeGenerator.cpp:1795. Done means the strongly typed INT8 engine builds successfully on Orin without weakening the deployment contract.