mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-15 14:43:48 +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
```
45 lines
1.2 KiB
JSON
45 lines
1.2 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:8000/v1/v1/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"prompt": "Respond to this question and explain your answer. Complete the sentence using one word: Roses are red, violets are ",
|
|
"stream": false,
|
|
"extra_body": {}
|
|
},
|
|
"endpoint": "/v1/completions",
|
|
"model": "Qwen/Qwen3-0.6B"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-52758d074c7541f99998bf277e553e78",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "length",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": " ____. \n\nThe sentence is: \"Roses are red, violets",
|
|
"stop_reason": null,
|
|
"prompt_logprobs": null
|
|
}
|
|
],
|
|
"created": 1757524112,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": {
|
|
"completion_tokens": 16,
|
|
"prompt_tokens": 25,
|
|
"total_tokens": 41,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|