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
```
197 lines
5.1 KiB
JSON
197 lines
5.1 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": true,
|
|
"temperature": 0.0,
|
|
"max_tokens": 5
|
|
},
|
|
"endpoint": "/v1/completions",
|
|
"model": "Qwen/Qwen3-0.6B"
|
|
},
|
|
"response": {
|
|
"body": [
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-7968eb721ac34b348eb879f300052b1b",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"text_offset": [
|
|
0
|
|
],
|
|
"token_logprobs": [
|
|
-0.031588248908519745
|
|
],
|
|
"tokens": [
|
|
"1"
|
|
],
|
|
"top_logprobs": [
|
|
{
|
|
"1": -0.031588248908519745
|
|
}
|
|
]
|
|
},
|
|
"text": "1",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524134,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-7968eb721ac34b348eb879f300052b1b",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"text_offset": [
|
|
1
|
|
],
|
|
"token_logprobs": [
|
|
-0.01468715537339449
|
|
],
|
|
"tokens": [
|
|
"9"
|
|
],
|
|
"top_logprobs": [
|
|
{
|
|
"9": -0.01468715537339449
|
|
}
|
|
]
|
|
},
|
|
"text": "9",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524134,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-7968eb721ac34b348eb879f300052b1b",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"text_offset": [
|
|
2
|
|
],
|
|
"token_logprobs": [
|
|
-0.30242931842803955
|
|
],
|
|
"tokens": [
|
|
"5"
|
|
],
|
|
"top_logprobs": [
|
|
{
|
|
"5": -0.30242931842803955
|
|
}
|
|
]
|
|
},
|
|
"text": "5",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524134,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-7968eb721ac34b348eb879f300052b1b",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": {
|
|
"text_offset": [
|
|
3
|
|
],
|
|
"token_logprobs": [
|
|
-1.2276304960250854
|
|
],
|
|
"tokens": [
|
|
"8"
|
|
],
|
|
"top_logprobs": [
|
|
{
|
|
"8": -1.2276304960250854
|
|
}
|
|
]
|
|
},
|
|
"text": "8",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524134,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-7968eb721ac34b348eb879f300052b1b",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "length",
|
|
"index": 0,
|
|
"logprobs": {
|
|
"text_offset": [
|
|
4
|
|
],
|
|
"token_logprobs": [
|
|
-0.7615041732788086
|
|
],
|
|
"tokens": [
|
|
","
|
|
],
|
|
"top_logprobs": [
|
|
{
|
|
",": -0.7615041732788086
|
|
}
|
|
]
|
|
},
|
|
"text": ",",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524134,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
}
|
|
}
|