e2e: Add OpenAI Content Array Test Case #925
Description
llm-d/llm-d-inference-sim#49 adds support for multimodal request payloads to the OpenAI chat completions API. An e2e test should be added to exercise the new content array of objects (instead of a plain string). For example:
curl -k -X POST http://localhost:8000/v1/chat/completions \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
"model": "inference-simulator-maas",
"messages": [
{
"role": "user",
"content": [
{ "type": "text", "text": "Can you describe this image?" },
{ "type": "image_url", "url": "https://example.com/image.png" }
]
}
]
}'Notes:
- A vllm-sim release with this PR is required before fixing this issue.
- The vllm-sim image ref will need to get bumped.