huggingface/optimum-intel v1.26.1

v1.26.1: Patch release

on GitHub

• Fix can_compile (#1511) by @jiqing-feng
• Fix preprocess_inputs for Gemma3 (#1507) by @rkazants
• Default config for Qwen3-30B-A3B (#1506) by @ljaljushkin
• Fix TasksManager._TRANSFORMERS_TASKS_TO_MODEL_LOADERS (#1501) by @echarlaix
• Fix some minor bugs after upgrading transformers to 4.55 for IPEX (#1485) by @kaixuanliu

Full Changelog: v1.26.0...v1.26.1

Compatible with transformers>=4.45,<4.56