Exportable kimi (#47096)
* Add Kimi-K2.5 exportability and standardize packed-vision attention
Exporter support for Kimi-K2.5 (vision/audio attention registered with the
reshaped vision-attention patch) plus:
- Kimi vision rotary now emits the standard packed (seq, head_dim) cos/sin
instead of the batched (1, seq, head_dim) LLM form, matching every other
vision encoder (no exporter-side normalization needed).
- ExecuTorch: materialise non-contiguous reshapes via a backend-local
_patch_reshape rather than an unconditional clone in the shared vision
patch, so ONNX/OpenVINO/dynamo graphs don't carry the copy.
- is_multimodal short-circuits to False for non-PreTrainedModel inputs.
- vision_utils.get_vision_cu_seqlens gains a merge_temporal option.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix
* address comments
* unified interpolation util
* fix version
* add attrs
* use linspace for bilinear cuz it's the only way for bit exact output
* maxDiff using unified arithmetic formula
* change expectations
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
