Fix KV260 PatchCore XModel compilation

[DeepKnowledge1]

🔗 Related Issue

Fixes #

📝 Description

• Add a KV260/DPU-friendly PatchCore inference graph.
• Simplify PatchCore operations to avoid compiler segmentation faults and unsupported CPU-heavy graph partitions.
• Restructure memory-bank similarity and reduction operations for Vitis AI KV260 compilation.
• Successfully compile the resulting XModel for DPUCZDX8G_ISA1_B4096 with a single DPU subgraph.

🔄 Type of Change

• 🐛 Bug fix (non-breaking change which fixes an issue)
• 🚀 New feature (non-breaking change which adds functionality)
• 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected)
• 📖 Documentation update
• 🏗️ Infrastructure / CI/CD update

🧪 Hardware & Matrix Testing

I have successfully built and tested this code using uv on:

• anomavision[cpu] (Standard/Edge)
• anomavision[cu121] (CUDA 12.1)
• anomavision[cu124] (CUDA 12.4)
• anomavision[cu118] (CUDA 11.8)

Host OS used for testing:

• Linux / Ubuntu
• Windows (Native or WSL2)
• macOS

🧪 KV260 / Vitis AI Validation

• Vitis AI PyTorch: 3.5.0+60df3f1+torch1.13.1
• PyTorch: 1.13.1
• Target: DPUCZDX8G_ISA1_B4096
• XModel quantization completed successfully.
• vai_c_xir compilation completed successfully.
• Result: 1 DPU subgraph, with CPU output conversion subgraphs only.

✅ Developer Checklist

• My code follows the core style guidelines of this project (Ruff/Black formatting).
• I have run uv run pytest and all unit tests pass locally.
• Lockfile Guard: If I added or modified a dependency in pyproject.toml, I have run uv lock --python 3.10 and committed the updated uv.lock file.
• I have added tests that prove my fix is effective or that my feature works.
• I have updated the documentation accordingly (if applicable).

📸 Screenshots / Visual Proof (Optional)

KV260 compiler output

[UNILOG][INFO] Graph name: PatchCoreKV260, with op num: 73
[UNILOG][INFO] Begin to compile...
[UNILOG][INFO] Total device subgraph number 4, DPU subgraph number 1
[UNILOG][INFO] Compile done.

The compiled XModel was generated successfully as deploy.xmodel.