unsloth/studio
Roland Tannous 4ef0453cc9 fix(studio): reject images in OpenAI tool passthrough for text-only GGUFs
The new tool passthrough branch runs before _extract_content_parts,
skipping the existing not is_vision guard. Requests combining tools
with an image on a text-only tool-capable GGUF were forwarded to
llama-server, producing opaque upstream errors instead of the
pre-existing clear 400. Restore the guard inline at the dispatch
point, checking both legacy image_base64 and inline image_url parts.
2026-04-16 21:10:26 +04:00
..
backend fix(studio): reject images in OpenAI tool passthrough for text-only GGUFs 2026-04-16 21:10:26 +04:00
frontend Chat first onboarding (#5063) 2026-04-16 09:58:10 -07:00
__init__.py Final cleanup 2026-03-12 18:28:04 +00:00
install_llama_prebuilt.py fix(rocm): tighten gfx regex to ignore generic ISA lines (#5033) 2026-04-15 05:24:41 -07:00
install_python_stack.py fix(rocm): tighten gfx regex to ignore generic ISA lines (#5033) 2026-04-15 05:24:41 -07:00
LICENSE.AGPL-3.0 Add AGPL-3.0 license to studio folder 2026-03-09 19:36:25 +00:00
setup.bat Final cleanup 2026-03-12 18:28:04 +00:00
setup.ps1 Trim verbose comments in PATH helpers 2026-04-16 12:01:01 +00:00
setup.sh Add AMD ROCm/HIP support across installer and hardware detection (#4720) 2026-04-10 01:56:12 -07:00
Unsloth_Studio_Colab.ipynb Allow install_python_stack to run on Colab (#4633) 2026-03-27 00:29:27 +04:00