mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
inference recordings from Qwen3-0.6B and vLLM 0.8.3 - ``` docker run --gpus all -v ~/.cache/huggingface:/root/.cache/huggingface -p 8000:8000 --ipc=host \ vllm/vllm-openai:latest \ --model Qwen/Qwen3-0.6B --enable-auto-tool-choice --tool-call-parser hermes ``` test with - ``` ./scripts/integration-tests.sh --stack-config server:ci-tests --setup vllm --subdirs inference ```
66 lines
2.2 KiB
JSON
66 lines
2.2 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:8000/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{
|
|
"type": "text",
|
|
"text": "Which planet do humans live on?"
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"stream": false,
|
|
"temperature": 0.0,
|
|
"max_tokens": 4096
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "Qwen/Qwen3-0.6B"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "chatcmpl-f7cda312aefe4a4ca4c34e7342f23802",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "<think>\nOkay, the user is asking which planet humans live on. Let me think. I know that humans are on Earth. But maybe they're confused because sometimes people think of other planets. I should clarify that Earth is the only planet where humans have been found. Also, maybe mention that Earth is a unique planet with all the necessary conditions for life. I should keep it simple and direct.\n</think>\n\nHumans live on **Earth**. This planet is unique in having the conditions necessary for life, such as liquid water, breathable air, and suitable temperatures.",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": [],
|
|
"reasoning_content": null
|
|
},
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524135,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": null,
|
|
"usage": {
|
|
"completion_tokens": 114,
|
|
"prompt_tokens": 15,
|
|
"total_tokens": 129,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
},
|
|
"prompt_logprobs": null
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|