v0.18.0

## What's Changed
* Revert "Revert "feat: Add CacheProvider API for external distributed caching"" by @deepme987 in https://github.com/Comfy-Org/ComfyUI/pull/12915
* fix(api-nodes): Tencent TextToModel and ImageToModel nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/12680
* Bump comfyui-frontend-package to 1.41.19 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/12923
* bump manager version to 4.1b4 by @ltdrdata in https://github.com/Comfy-Org/ComfyUI/pull/12930
* comfy aimdo 0.2.11 + Improved RAM Pressure release strategies - Windows speedups by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12925
* Update README. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12931
* comfy-aimdo 0.2.12 by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12941
* fix: use no-store cache headers to prevent stale frontend chunks by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12911
* feat: Support mxfp8 by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/12907
* Add --fp16-intermediates to use fp16 for intermediate values between … by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12953
* Update comfyui-frontend-package to version 1.41.20 by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12954
* LTXV: Accumulate VAE decode results on intermediate_device by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/12955
* bump manager version to 4.1b5 by @ltdrdata in https://github.com/Comfy-Org/ComfyUI/pull/12957
* ops: opt out of deferred weight init if subclassed by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/12967
* Make EmptyLatentImage follow intermediate dtype. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/12974
* Enable Pytorch Attention for AMD gfx1150 (Strix Point) by @lostdisc in https://github.com/Comfy-Org/ComfyUI/pull/12973
* feat: add essentials_category to nodes and blueprints for Essentials tab by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12573
* feat(assets): align local API with cloud spec by @luke-mino-altherr in https://github.com/Comfy-Org/ComfyUI/pull/12863
* ci: add check to block AI agent Co-authored-by trailers in PRs by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12799
* Skip running model finalizers at exit by @blepping in https://github.com/Comfy-Org/ComfyUI/pull/12994
* Add --enable-dynamic-vram options to force enable it. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13002
* [Trainer] FP4, 8, 16 training by native dtype support and quant linear autograd function by @KohakuBlueleaf in https://github.com/Comfy-Org/ComfyUI/pull/12681
* Fix potential issue. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13009
* fix: atomic writes for userdata to prevent data loss on crash by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12987
* Disable SageAttention for Hunyuan3D v2.1 DiT by @paulomuggler in https://github.com/Comfy-Org/ComfyUI/pull/12772
* Update workflow templates to v0.9.26 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/13012
* Mark weight_dtype as advanced input in Load Diffusion Model node by @christian-byrne in https://github.com/Comfy-Org/ComfyUI/pull/12769
* Reduce LTX VAE VRAM usage and save use cases from OOMs/Tiler by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/13013
* Reduce WAN VAE VRAM, Save use cases for OOM/Tiler by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/13014
* bump manager version to 4.1b6 by @ltdrdata in https://github.com/Comfy-Org/ComfyUI/pull/13022
* Inplace VAE output processing to reduce peak RAM consumption. by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/13028
* Fix case where pixel space VAE could cause issues. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13030
* cascade: remove dead weight init code by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/13026
* fix: run text encoders on MPS GPU instead of CPU for Apple Silicon by @k06a in https://github.com/Comfy-Org/ComfyUI/pull/12809
* fix(api-nodes): add support for "thought_image" in Nano Banana 2 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/13038
* Update comfyui-frontend-package version to 1.41.21 by @DrJKL in https://github.com/Comfy-Org/ComfyUI/pull/13035
* Make more intermediate values follow the intermediate dtype. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13051
* Further Reduce LTX VAE decode peak RAM usage by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/13052
* Fix regression. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13053
* fp16 intermediates doen't work for some text enc models. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13056
* ltx: vae: implement chunked encoder + CPU IO chunking (Big VRAM reductions) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/13062
* memory: Add more exclusion criteria to pinned read (fixes corrupt outputs - rare cases) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/13067
* Reduce tiled decode peak memory by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/13050
* Revert "fix: run text encoders on MPS GPU instead of CPU for Apple Silicon" by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13070
* Fix VRAM leak in tiler fallback in video VAEs by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/13073
* ltx: vae: Fix missing init variable by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/13074
* [API Nodes] mark seedream-3-0-t2i and seedance-1-0-lite models as deprecated by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/13060
* Add slice_cond and per-model context window cond resizing by @drozbay in https://github.com/Comfy-Org/ComfyUI/pull/12645
* feat(api-nodes): add Quiver SVG nodes by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/13047
* Make EmptyImage node follow intermediate device/dtype. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/13079
* Move inline comfy.context_windows imports to top-level in model_base.py by @Kosinkadink in https://github.com/Comfy-Org/ComfyUI/pull/13083

## New Contributors
* @lostdisc made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/12973
* @paulomuggler made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/12772
* @k06a made their first contribution in https://github.com/Comfy-Org/ComfyUI/pull/12809

**Full Changelog**: https://github.com/Comfy-Org/ComfyUI/compare/v0.17.0...v0.18.0