vai-partition-analysis

Inspect the result of a VAIML compilation of a mixed-precision ONNX model and reduce the number of NPU partitions toward a single partition. Parses the compiler operation statistics (matched kernels / templated graphs), the partition count, and the AIE/CPU offload split; when more than one partition is produced, reads the CpuBecause messages and compilation warnings, classifies them, and proposes remediation. Remediation prefers the correct frontend (fe_args) flags over model patching; when the partition break originates from quantization, it proposes Quark configuration changes instead. Every proposed change is followed by a re-compilation to evaluate the result.

Version

6.3.0

License

Apache-2.0 WITH LLVM-exception

Compatibility

Requires VitisAI 6.3+