What's Changed

• chore: fix the wheel hf uploading by @lmxyy in #599
• fix: enable correct batch processing in teacache by @Bluear7878 in #601
• chore: bump the version to v1.0.0 by @lmxyy in #602
• feat: pythonized model and QwenImage Support by @lmxyy in #593
• feat: FLUX Gradio demos support FP4 by @lmxyy in #623
• Fix ValueError in NunchakuQwenImagePipeline.prepare_latents unpacking by @ighoshsubho in #616
• feat: support Qwen-Image in ComfyUI-nunchaku by @lmxyy in #632
• feat: support lightning Qwen-Image models by @lmxyy in #641
• feat: Implement V2 FBCaching and Optimize Existing FBCache by @Bluear7878 in #621
• feat: add support for teacache in flux kontext by @BoynChan in #618
• feat: add paddings if LoRA ranks for q, k, v are different by @woct0rdho in #603
• fix: close the NVFP4 performance gap between the Python backend and C backend by @lmxyy in #647
• feat: add support for python 3.13 by @DrZhouKarl in #651
• feat: async CPU offloading for Python backend by @lmxyy in #624
• feat: simplify the implementation of the async offloading and support ComfyUI offloading by @lmxyy in #655
• docs: add the docstrings for v1.0.0 by @lmxyy in #656
• chore: release nunchaku v1.0.0 by @lmxyy in #658

New Contributors

• @ighoshsubho made their first contribution in #616
• @BoynChan made their first contribution in #618
• @woct0rdho made their first contribution in #603
• @DrZhouKarl made their first contribution in #651

Full Changelog: v0.3.2...v1.0.0