mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 06:23:45 +00:00
bb5dc85012
# What does this PR do? Allows passing through extra_body parameters to inference providers. closes #2720 ## Test Plan CI and added new test
45 lines
1.1 KiB
JSON
45 lines
1.1 KiB
JSON
{
|
|
"test_id": null,
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:8000/v1/v1/models",
|
|
"headers": {},
|
|
"body": {},
|
|
"endpoint": "/v1/models",
|
|
"model": ""
|
|
},
|
|
"response": {
|
|
"body": [
|
|
{
|
|
"__type__": "openai.types.model.Model",
|
|
"__data__": {
|
|
"id": "Qwen/Qwen3-0.6B",
|
|
"created": 1760135828,
|
|
"object": "model",
|
|
"owned_by": "vllm",
|
|
"root": "Qwen/Qwen3-0.6B",
|
|
"parent": null,
|
|
"max_model_len": 4096,
|
|
"permission": [
|
|
{
|
|
"id": "modelperm-5119df1e8c3246148a1d43e60357e420",
|
|
"object": "model_permission",
|
|
"created": 1760135828,
|
|
"allow_create_engine": false,
|
|
"allow_sampling": true,
|
|
"allow_logprobs": true,
|
|
"allow_search_indices": false,
|
|
"allow_view": true,
|
|
"allow_fine_tuning": false,
|
|
"organization": "*",
|
|
"group": null,
|
|
"is_blocking": false
|
|
}
|
|
]
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": false
|
|
},
|
|
"id_normalization_mapping": {}
|
|
}
|