Text Generation Webui – v3.16
🚀 Text Generation WebUI v3.16 just dropped—and it’s a game-changer for local LLM folks!
New portable build via symlink? Yes, please. Devs juggling multiple setups can now switch models and configs without reinstalling. Big shoutout to @reksar! 🙌
macOS Apple Silicon users—your day is saved. Python deps now work flawlessly on Tahoe (thanks @drieschel)! 🍎
Backend upgrades? Oh yeah:
- llama.cpp updated to latest GGML fork → now supports Llama-Mini-2.0 and Ring-Mini-2.0! Tiny but mighty models, unlocked.
- ExLlamaV3 v0.0.11 = faster inference, smoother text flow.
- Triton-Windows updated to 3.5.0.post21 → better CUDA perf on Windows rigs.
Portable builds are now even easier:
📥 Download → 📦 Unzip → 💾 Copy your old `user_data` folder in → ✅ All models, themes, and settings preserved. No pip. No venvs. Just AI magic.
Pick your build:
- NVIDIA? → `cuda12.4` (new) or `cuda11.7` (legacy)
- AMD/Intel? → Use `vulkan`
- CPU-only? → `cpu` build
- Mac? → `macos-arm64` (M-series) or `macos-x86_64`
No install. No fuss. Just drop-in, run, and chat with your LLMs like never before. 🚀