- Change ChatCompletionRequest.stream default from True to False per OpenAI spec — curl without "stream" now returns a single JSON object - Fix non-streaming chat completions to include usage stats (was all 0s) - Add POST /v1/responses implementing OpenAI's Responses API format: accepts input as string or typed message array, returns Response objects with output_text content, supports both streaming and non-streaming modes |
||
|---|---|---|
| .. | ||
| backend | ||
| frontend | ||
| __init__.py | ||
| install_llama_prebuilt.py | ||
| install_python_stack.py | ||
| LICENSE.AGPL-3.0 | ||
| setup.bat | ||
| setup.ps1 | ||
| setup.sh | ||
| Unsloth_Studio_Colab.ipynb | ||