Text Generation Webui – v4.5.1
Big news for all the local LLM enthusiasts! The project formerly known as text-generation-webui has officially undergone a massive rebranding to TextGen! 🚀
This latest update (v4.5.1) is all about stability, UI polish, and critical optimizations for the Gemma 4 model family. Whether you are running heavy quantizations or experimenting with complex tool calling, this release brings essential tweaks under the hood to keep your local inference smooth.
What’s New in This Release:
- Identity Shift: The project is now officially TextGen! You can find the updated repository at `github.com/oobabooga/textgen`.
- Gemma 4 Optimization: Significant fixes for Gemma 4 tool calling, including much better handling of quotes and newlines, plus improved rendering for consecutive “thinking” blocks.
- VRAM Efficiency: A huge win for GPU users! There is a much-needed reduction in VRAM peak usage during the prompt logprobs forward pass—perfect for squeezing more performance out of your hardware. 🧠
- UI Enhancements: Added a fresh sky-blue color for quoted text in light mode and improved logits display to make debugging easier.
- Bug Squashing:
- Fixed chat scroll issues when interacting with “thinking” blocks.
- Resolved tool icon SVG shrinking during long tool calls.
- Fixed various BOS/EOS token issues for models lacking specific chat templates.
- Dependency Updates: Includes fresh updates for both `llama.cpp` and the `ik_llama.cpp` fork, bringing those awesome new quantization types to your workflow.
Pro-Tip for Tinkerers: 🛠️
If you use the portable builds, updating is a breeze! Just download the latest version, extract it, and swap your existing `user_data` folder into the new directory. Even better, since version 4.0, you can place `user_data` one level up next to your install folder so multiple versions can share the same models and settings!