llama-stack-mirror/llama_stack
Dinesh Yeduguru 194f6f01c6 Tgi fixture (#519)
# What does this PR do?

* Add a test fixture for tgi
* Fixes the logic to correctly pass the llama model for chat completion

Fixes #514

## Test Plan

pytest -k "tgi"
llama_stack/providers/tests/inference/test_text_inference.py --env
TGI_URL=http://localhost:$INFERENCE_PORT --env TGI_API_TOKEN=$HF_TOKEN
2024-11-27 14:37:58 -08:00
..
apis Fix opentelemetry adapter (#510) 2024-11-27 14:37:57 -08:00
cli No need to use os.path.relpath() when Path() knows everything anyway 2024-11-27 14:37:58 -08:00
distribution Ensure model_local_dir does not mangle "C:\" on Windows 2024-11-27 14:37:58 -08:00
providers Tgi fixture (#519) 2024-11-27 14:37:58 -08:00
scripts Integrate distro docs into the restructured docs 2024-11-20 23:20:05 -08:00
templates Mark some pages as not-in-toctree explicitly 2024-11-27 14:37:58 -08:00
__init__.py API Updates (#73) 2024-09-17 19:51:35 -07:00