mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 14:27:58 +00:00
# What does this PR do? Allows passing through extra_body parameters to inference providers. closes #2720 ## Test Plan CI and added new test
48 lines
1.3 KiB
JSON
48 lines
1.3 KiB
JSON
{
|
|
"test_id": "tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B]",
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:8000/v1/v1/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"prompt": "I am feeling really sad today.",
|
|
"stream": false
|
|
},
|
|
"endpoint": "/v1/completions",
|
|
"model": "Qwen/Qwen3-0.6B"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "rec-d2ba309413e8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "length",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": " I have been working on a project that I feel like I'm not doing well",
|
|
"stop_reason": null,
|
|
"prompt_logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": {
|
|
"completion_tokens": 16,
|
|
"prompt_tokens": 7,
|
|
"total_tokens": 23,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
},
|
|
"service_tier": null,
|
|
"kv_transfer_params": null
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
},
|
|
"id_normalization_mapping": {}
|
|
}
|