mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-15 22:47:59 +00:00
c2a9c65fff
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
```
124 lines
3.4 KiB
JSON
124 lines
3.4 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:8000/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"content": [
|
|
{
|
|
"type": "text",
|
|
"text": "You are a helpful assistant. Michael Jordan was born in 1963. He played basketball for the Chicago Bulls for 15 seasons."
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{
|
|
"type": "text",
|
|
"text": "Please give me information about Michael Jordan."
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"extra_body": {
|
|
"guided_json": {
|
|
"$defs": {
|
|
"NBAStats": {
|
|
"properties": {
|
|
"year_for_draft": {
|
|
"title": "Year For Draft",
|
|
"type": "integer"
|
|
},
|
|
"num_seasons_in_nba": {
|
|
"title": "Num Seasons In Nba",
|
|
"type": "integer"
|
|
}
|
|
},
|
|
"required": [
|
|
"year_for_draft",
|
|
"num_seasons_in_nba"
|
|
],
|
|
"title": "NBAStats",
|
|
"type": "object"
|
|
}
|
|
},
|
|
"properties": {
|
|
"first_name": {
|
|
"title": "First Name",
|
|
"type": "string"
|
|
},
|
|
"last_name": {
|
|
"title": "Last Name",
|
|
"type": "string"
|
|
},
|
|
"year_of_birth": {
|
|
"title": "Year Of Birth",
|
|
"type": "integer"
|
|
},
|
|
"nba_stats": {
|
|
"$ref": "#/$defs/NBAStats"
|
|
}
|
|
},
|
|
"required": [
|
|
"first_name",
|
|
"last_name",
|
|
"year_of_birth",
|
|
"nba_stats"
|
|
],
|
|
"title": "AnswerFormat",
|
|
"type": "object"
|
|
}
|
|
},
|
|
"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-ba863ae481964bcca497a7feba2a2689",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "{\"first_name\": \"Michael\", \"last_name\": \"Jordan\", \"year_of_birth\": 1963, \"nba_stats\": {\"year_for_draft\": 1984, \"num_seasons_in_nba\": 15}}",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": [],
|
|
"reasoning_content": null
|
|
},
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524142,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": null,
|
|
"usage": {
|
|
"completion_tokens": 61,
|
|
"prompt_tokens": 51,
|
|
"total_tokens": 112,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
},
|
|
"prompt_logprobs": null
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|