unsloth/studio
Roland Tannous aae1059d90 studio(frontend): send all GGUF formats in one request
Drop the per-format serial loop that called exportGGUF once per item
in quantLevels. quantLevels is already a string[]; pass it directly so
multi-format selections become one POST instead of N sequential POSTs.

Eliminates the wasted weight-merge between formats and lets the backend
route all formats through save_pretrained_gguf's native list handling.
Closes the studio-side half of the batch GGUF export work.
2026-04-14 23:39:13 +04:00
..
backend studio: ExportBackend.export_gguf batch call + try/finally relocation 2026-04-14 23:12:59 +04:00
frontend studio(frontend): send all GGUF formats in one request 2026-04-14 23:39:13 +04:00
__init__.py Final cleanup 2026-03-12 18:28:04 +00:00
install_llama_prebuilt.py Add AMD ROCm/HIP support across installer and hardware detection (#4720) 2026-04-10 01:56:12 -07:00
install_python_stack.py Pin bitsandbytes to continuous-release_main on ROCm (4-bit decode fix) (#4954) 2026-04-10 06:25:39 -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 split venv_t5 into tiered 5.3.0/5.5.0 and fix trust_remote_code (#4878) 2026-04-07 20:05:01 +04:00
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