What's Changed

• Model builder refactoring by @tianleiwu in https://github.com/microsoft/onnxruntime-genai/pull/1862
• Add lintrunner to format code by @tianleiwu in https://github.com/microsoft/onnxruntime-genai/pull/1884
• Remove empty submodule leftover. by @xkszltl in https://github.com/microsoft/onnxruntime-genai/pull/1883
• Fix build for lack of RTLD_DI_ORIGIN support by @jaeyoonjung in https://github.com/microsoft/onnxruntime-genai/pull/1888
• Enable graph capture for webgpu by @qjia7 in https://github.com/microsoft/onnxruntime-genai/pull/1848
• Generic shared emb_tokens/lm_head implementation by @jixiongdeng in https://github.com/microsoft/onnxruntime-genai/pull/1885
• Fix bug in Squeeze for getting the value of total_seq_len by @Honry in https://github.com/microsoft/onnxruntime-genai/pull/1886
• Extra_options disable_qkv_fusion to untie qkv_projs from upstream choice by @jixiongdeng in https://github.com/microsoft/onnxruntime-genai/pull/1893
• Fix mac pipeline by @apsonawane in https://github.com/microsoft/onnxruntime-genai/pull/1904
• whisper: Support a variant of the whisper pipeline where encoder / decoder are stateful. by @RyanMetcalfeInt8 in https://github.com/microsoft/onnxruntime-genai/pull/1857