[Copilot]

Description

• Buffer preservation: Copy tokens when input/output buffers alias, independently of routing-weight normalization.
• Regression coverage: Cover graph inputs, Add and Reshape(Add) producers, intermediate/exposed MoE outputs, and both normalization modes.

Motivation and Context

CPU MoE can return incorrect results in Add → MoE → Relu when routing normalization is disabled. Its in-place allocation contract permits output to reuse token storage, but clearing that output destroys tokens before expert computation reads them.

• Fixes CPU MoE gives wrong results when its input is computed in the graph and its output feeds another node #33866

[azure-pipelines]

Azure Pipelines:
There may be pipelines that require an authorized user to comment /azp run to run.

[Copilot]

🟢 Approval recommended

No active review issues were identified for the CPU MoE buffer-aliasing fix.

No open issues 🎉

What changed in this PR

Fixes CPU MoE input corruption when its output reuses token storage, addressing #33866 without tying buffer preservation to routing-weight normalization.

Changes:

• Copies tokens before clearing the output when input and output buffers alias.
• Adds float32 and float16 regression tests covering graph inputs, Add and Reshape(Add) producers, intermediate and exposed MoE outputs, both normalization modes, and repeated runs.

File	Description
onnxruntime/​test/​contrib_ops/​moe_test.cc	Adds regression coverage for CPU MoE buffer reuse across graph configurations.
onnxruntime/​contrib_ops/​cpu/​moe/​moe_cpu.cc	Preserves tokens whenever input and output buffers alias.

_{Review effort: Balanced}