phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-12 04:50:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docs: improve integration test doc

Browse source 
Signed-off-by: reidliu <reid201711@gmail.com>
This commit is contained in:
reidliu 2025-03-08 09:50:10 +08:00
parent 0db3a2f511
commit 791fd43694
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tests/integration/README.md
View file

@ -55,7 +55,7 @@ Running all inference tests for a number of models:
TEXT_MODELS=meta-llama/Llama-3.1-8B-Instruct,meta-llama/Llama-3.1-70B-Instruct
VISION_MODELS=meta-llama/Llama-3.2-11B-Vision-Instruct
EMBEDDING_MODELS=all-MiniLM-L6-v2
TOGETHER_API_KEY=...
export TOGETHER_API_KEY=<together_api_key>
pytest -s -v tests/api/inference/ \
--stack-config=together \
@ -67,7 +67,7 @@ pytest -s -v tests/api/inference/ \
Same thing but instead of using the distribution, use an adhoc stack with just one provider (`fireworks` for inference):
```bash
FIREWORKS_API_KEY=...
export FIREWORKS_API_KEY=<fireworks_api_key>
pytest -s -v tests/api/inference/ \
--stack-config=inference=fireworks \