llama-stack-mirror/llama_toolchain/inference/adapters/tgi
2024-09-04 22:35:22 -07:00
..
__init__.py TGI adapter and some refactoring of other inference adapters 2024-09-04 22:35:22 -07:00
tgi.py Use the lower-level generate_stream() method for correct tool calling 2024-09-04 22:35:22 -07:00