6c493b4076The prebuilt bundles ship llama-diffusion-gemma-visual-server, but runtime_patterns_for_choice pruned it, so a fresh install never placed it next to llama-server. ensure_diffusion_visual_server then found no standalone release asset and skipped it, leaving Studio unable to serve DiffusionGemma GGUFs natively (it required DG_VISUAL_BIN or a source build). Keep the binary in the runtime allowlist on Linux, macOS and Windows so it lands in build/bin and is activated automatically. |
||
|---|---|---|
| .. | ||
| backend | ||
| frontend | ||
| src-tauri | ||
| __init__.py | ||
| install_llama_prebuilt.py | ||
| install_python_stack.py | ||
| LICENSE.AGPL-3.0 | ||
| package-lock.json | ||
| package.json | ||
| setup.bat | ||
| setup.ps1 | ||
| setup.sh | ||
| Unsloth_Studio_Colab.ipynb | ||