feat(rope_fix): Hoist layer-invariant RoPE indexing out of decoder su…

[quic-rishinr]

…bfunctions for cached text models (#928)

This change moves layer-invariant RoPE cos/sin indexing out of repeated decoder-layer subfunctions and into model-level forward paths.

For cached decoder models, we were repeatedly doing:

cos = cos[position_ids].unsqueeze(1)
sin = sin[position_ids].unsqueeze(1)

inside each decoder attention block. With ONNX subfunctions enabled, that indexing becomes part of the exported repeated subfunction body and contributes to the on-device regression we observed after the single-subfunction Rope Fix work #880 .

This patch hoists that work once per forward pass and passes the already-shaped cos/sin tensors into each decoder layer.

Applied the refactor to the applicable QEff model families that thread static cached RoPE tensors through repeated decoder layers, including:

• Llama
• Llama SwiftKV
• Gemma
• Gemma2
• Mistral
• Falcon
• GPT-OSS
• Granite
• GraniteMoE
• Mllama text path
• Mixtral
• Olmo2
• Phi3
• Qwen2
• Qwen3
• Qwen3 MoE
• Qwen2.5 VL text path
• Qwen3 VL text path
• Qwen3 VL MoE text path

For the Qwen VL text towers, the same idea is applied to the indexed/interleaved MRoPE preparation: the already-indexed cos/sin tensors are prepared once before the decoder-layer loop and reused across layers.

Added a TinyLlama regression test to assert that export with subfunctions still produces a single decoder-layer ONNX function.

Verified:

python -m pytest -q tests/unit_test/models/test_model_quickcheck.py -n auto

---

[vbaddi]

duplicate #928 not need in release branch, closing the PR