v0.3.69

## What's Changed
* Use single apply_rope function across models by @contentis in https://github.com/comfyanonymous/ComfyUI/pull/10547
* Lower ltxv mem usage to what it was before previous pr. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10643
* feat(API-nodes): use new client in Rodin3D nodes; remove old api client by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10645
* Fix qwen controlnet regression. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10657
* Enable pinned memory by default on Nvidia. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10656
* Pinned mem also seems to work on AMD. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10658
* Clarify release cycle. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10667
* Tell users they need to upload their logs in bug reports. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10671
* mm: guard against double pin and unpin explicitly by @rattus128 in https://github.com/comfyanonymous/ComfyUI/pull/10672
* Only unpin tensor if it was pinned by ComfyUI by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10677
* Make ScaleROPE node work on Flux. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10686
* Add logging for model unloading. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10692
* Unload weights if vram usage goes up between runs. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10690
* ops: Put weight cast on the offload stream - Fixes --async-offload black screen by @rattus128 in https://github.com/comfyanonymous/ComfyUI/pull/10697
* Update CI workflow to remove dead macOS runner. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10704
* Don't pin tensor if not a torch.nn.parameter.Parameter by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10718
* Update README.md for Intel Arc GPU installation, remove IPEX by @qiacheng in https://github.com/comfyanonymous/ComfyUI/pull/10729
* always unload re-used but modified models - Fixed bad outputs in some Upscaler / Lora flows by @rattus128 in https://github.com/comfyanonymous/ComfyUI/pull/10724
* qwen: reduce VRAM usage by @rattus128 in https://github.com/comfyanonymous/ComfyUI/pull/10725
* Update Python 3.14 compatibility notes in README  by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10730
* Quantized Ops fixes by @contentis in https://github.com/comfyanonymous/ComfyUI/pull/10715
* add PR template for API-Nodes by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10736
* feat: add create_time dict to prompt field in /history and /queue by @ric-yu in https://github.com/comfyanonymous/ComfyUI/pull/10741
* flux: reduce VRAM usage by @rattus128 in https://github.com/comfyanonymous/ComfyUI/pull/10737
* Better instructions for the portable. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10743
* Use same code for chroma and flux blocks so that optimizations are shared. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10746
* Fix custom nodes import error. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10747
* Add left padding support to tokenizers. by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10753
* [API Nodes] mark OpenAIDalle2 and OpenAIDalle3 nodes as deprecated by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10757
* Revert "mark OpenAIDalle2 and OpenAIDalle3 nodes as deprecated (#10757)" by @bigcat88 in https://github.com/comfyanonymous/ComfyUI/pull/10759
* Change ROCm nightly install command to 7.1 by @comfyanonymous in https://github.com/comfyanonymous/ComfyUI/pull/10764

## New Contributors
* @ric-yu made their first contribution in https://github.com/comfyanonymous/ComfyUI/pull/10741

**Full Changelog**: https://github.com/comfyanonymous/ComfyUI/compare/v0.3.68...v0.3.69