ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
unsloth/studio/backend/core
History
Roland Tannous 0e7c8a2e5e Switch GGUF backend from /v1/completions to /v1/chat/completions 
Fixes two bugs:
1. Chat template tags (<|im_start|>, <|im_end|>) leaking into output
   because /v1/completions treated them as literal text
2. Image hallucination because image_b64 was never passed to llama-server

Now llama-server handles chat templates natively and receives images
as OpenAI-format multimodal content parts for vision models.
2026-02-24 19:21:01 +04:00
..
export fix: skip sudo check on WSL during GGUF export to prevent password prompt hang 2026-02-17 19:30:02 +00:00
inference Switch GGUF backend from /v1/completions to /v1/chat/completions 2026-02-24 19:21:01 +04:00
training Cap dataset.map num_proc on multi-GPU machines to prevent fork deadlocks 2026-02-23 14:25:31 +00:00
__init__.py refactor: remove gradio dependency from training backend 2026-02-13 09:25:49 +00:00