mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-16 06:53:47 +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
```
70 lines
1.8 KiB
JSON
70 lines
1.8 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:8000/v1/v1/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"prompt": "Hello, world!",
|
|
"stream": false,
|
|
"extra_body": {
|
|
"prompt_logprobs": 0
|
|
}
|
|
},
|
|
"endpoint": "/v1/completions",
|
|
"model": "Qwen/Qwen3-0.6B"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-f7da1cba36ba427c8acd9ad2f0722fa4",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "length",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": " I'm a 3-year-old girl who loves to play with my cat.",
|
|
"stop_reason": null,
|
|
"prompt_logprobs": [
|
|
null,
|
|
{
|
|
"11": {
|
|
"logprob": -8.8668212890625,
|
|
"rank": 1031,
|
|
"decoded_token": ","
|
|
}
|
|
},
|
|
{
|
|
"1879": {
|
|
"logprob": -4.7821879386901855,
|
|
"rank": 10,
|
|
"decoded_token": "\u0120world"
|
|
}
|
|
},
|
|
{
|
|
"0": {
|
|
"logprob": -1.6575366258621216,
|
|
"rank": 2,
|
|
"decoded_token": "!"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"created": 1757524144,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": {
|
|
"completion_tokens": 16,
|
|
"prompt_tokens": 4,
|
|
"total_tokens": 20,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|