llama-stack-mirror/tests/integration/recordings/responses/6cf57d8dfcfc.json
Matthew Farrellee c2a9c65fff chore: update the vLLM inference impl to use OpenAIMixin for openai-compat functions
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
```
2025-09-10 10:10:10 -04:00

86 lines
2.2 KiB
JSON

{
"request": {
"method": "POST",
"url": "http://localhost:8000/v1/v1/completions",
"headers": {},
"body": {
"model": "Qwen/Qwen3-0.6B",
"prompt": "<|begin_of_text|>Complete the sentence: Micheael Jordan is born in ",
"logprobs": 1,
"stream": false,
"temperature": 0.0,
"max_tokens": 5
},
"endpoint": "/v1/completions",
"model": "Qwen/Qwen3-0.6B"
},
"response": {
"body": {
"__type__": "openai.types.completion.Completion",
"__data__": {
"id": "cmpl-b114bec84b5a430ba94520ac9e7a6d8d",
"choices": [
{
"finish_reason": "length",
"index": 0,
"logprobs": {
"text_offset": [
0,
1,
2,
3,
4
],
"token_logprobs": [
-0.03187580779194832,
-0.014971747994422913,
-0.3393988609313965,
-1.2200194597244263,
-0.762129545211792
],
"tokens": [
"1",
"9",
"5",
"8",
","
],
"top_logprobs": [
{
"1": -0.03187580779194832
},
{
"9": -0.014971747994422913
},
{
"5": -0.3393988609313965
},
{
"8": -1.2200194597244263
},
{
",": -0.762129545211792
}
]
},
"text": "1958,",
"stop_reason": null,
"prompt_logprobs": null
}
],
"created": 1757524133,
"model": "Qwen/Qwen3-0.6B",
"object": "text_completion",
"system_fingerprint": null,
"usage": {
"completion_tokens": 5,
"prompt_tokens": 18,
"total_tokens": 23,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}
},
"is_streaming": false
}
}