Guang Yang

Make StaticCache configurable at model construct time

8

# What does this PR do? This PR is to address #32500 for ["Export to ExecuTorch"](https://github.com/huggingface/transformers/issues/32253) Enable the ability to load a model with options to statically config the model...

Core ML perf regression observed on non-genai models

5

### 🐛 Describe the bug We are running exercise on the [newly launched benchmarking infra](https://github.com/pytorch/executorch/tree/main/extension/benchmark) with the in-tree enabled models under `examples/models`. You can follow the instruction to extract and...