Update blog

Author: cmdr2

content/blog/2025-12-25-1766652519.md

@@ -0,0 +1,15 @@
+---
+title: "Post from Dec 25, 2025"
+date: 2025-12-25T08:48:39
+slug: "1766652519"
+tags:
+  - worklog
+  - easydiffusion
+---
+
+- Enabled Flash-Attention and CPU offloading by default in sdkit3 (i.e. Easy Diffusion v4).
+- Added optional VAE tiling (and VAE tile size configuration) via `config.yaml` in Easy Diffusion v4.
+- Created Easy Diffusion's [fork](https://github.com/easydiffusion/stable-diffusion-webui-forge) of Forge WebUI, in order to apply the patches required to run with ED. And also to try adding new features like Z-Image (which are missing in the seemingly-abandoned main Forge repo).
+- Improved the heuristics used for killing and restarting the backend child process, since `/ping` requests are unreliable if the backend is under heavy load.
+- Merged a few PRs ([1](https://github.com/easydiffusion/torchruntime/pull/28) [2](https://github.com/easydiffusion/torchruntime/pull/30)) for `torchruntime` that improve support for pinning pre-cu128 torch versions and fix the order of detection of DirectML and CUDA (prefers CUDA).
+- Added progress bars when downloading v4 backend artifacts.