[AMD NPU] models fail to load with "invalid unordered_map<K,T> key" on Foundry Local 0.8.113

Nobody has claimed this yet.

**Description**

On AMD Ryzen AI systems, all AMD Vitis NPU models fail during the load step in Foundry Local, even though the models download successfully and appear in the local cache. The error occurs consistently across multiple models (Phi-4-mini, Qwen2.5-Coder, etc.).

**Environment**

Foundry Local version:
0.8.113+70167233c5

AMD NPU Execution Provider (Windows ML):
Name: MicrosoftCorporationII.WinML.AMD.NPU.EP.1.8
Version: 1.8.26.0
OS: Windows 11 24H2 (Copilot+ PC)

**Repro Steps**

```
foundry model run qwen2.5-coder-7b-instruct-vitis-npu
```

**Expected Behavior**

Model should load successfully into Foundry Local service and be available via local OpenAI-compatible endpoint.

**Actual Behavior**

Fails during EP initialization with:

`invalid unordered_map key" `

**Additional Notes**

- CPU variants load and run fine.
- NPU EP and Foundry Local are both latest versions.
- This appears identical to Issue #327

Start by reproducing the failure with `foundry model run qwen2.5-coder-7b-instruct-vitis-npu` on an AMD Ryzen AI system, then compare the behavior and discussion with Issue #327. Trace the AMD NPU execution-provider initialization that produces `invalid unordered_map key`; done means Vitis NPU models load and become available through the local OpenAI-compatible endpoint.

Written by the indexing model from the issue text.