mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-16 23:03:49 +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
```
524 lines
14 KiB
JSON
524 lines
14 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:8000/v1/v1/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"prompt": "<|begin_of_text|>Return the exact same sentence and don't add additional words): Michael Jordan was born in the year of 1963",
|
|
"stream": true,
|
|
"temperature": 0.0,
|
|
"max_tokens": 50,
|
|
"stop": [
|
|
"1963"
|
|
]
|
|
},
|
|
"endpoint": "/v1/completions",
|
|
"model": "Qwen/Qwen3-0.6B"
|
|
},
|
|
"response": {
|
|
"body": [
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": ".",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": " <|",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "end",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "_of_t",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "e",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "xt|",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": ">\n",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "\n",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "*",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "*A",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": ".** Mich",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "ael Jor",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "dan ",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "was b",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "orn",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": " in ",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "the y",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "ear",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": " ",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "o",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "f",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": " ",
|
|
"stop_reason": null
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-8ca2b3d09fbe49f99b86bc496a6c4bf8",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "",
|
|
"stop_reason": "1963"
|
|
}
|
|
],
|
|
"created": 1757524133,
|
|
"model": "Qwen/Qwen3-0.6B",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": null
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
}
|
|
}
|