llama-stack-mirror/tests/integration/inference/recordings/6626c46dfaf503c589013d6396a3e6871117c7c024d37f16a8d0b2a7def9f8ed.json
Eric Huang c76bf97ccf test, recording
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
2025-10-08 14:57:06 -07:00

59 lines
1.8 KiB
JSON

{
"test_id": "tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming_suffix[txt=ollama/llama3.2:3b-instruct-fp16-inference:completion:suffix]",
"request": {
"method": "POST",
"url": "http://localhost:11434/api/ps",
"headers": {},
"body": {},
"endpoint": "/api/ps",
"model": ""
},
"response": {
"body": {
"__type__": "ollama._types.ProcessResponse",
"__data__": {
"models": [
{
"model": "llama3.2:3b-instruct-fp16",
"name": "llama3.2:3b-instruct-fp16",
"digest": "195a8c01d91ec3cb1e0aad4624a51f2602c51fa7d96110f8ab5a20c84081804d",
"expires_at": "2025-10-08T14:29:44.502767-07:00",
"size": 8581748736,
"size_vram": 8581748736,
"details": {
"parent_model": "",
"format": "gguf",
"family": "llama",
"families": [
"llama"
],
"parameter_size": "3.2B",
"quantization_level": "F16"
},
"context_length": null
},
{
"model": "llama-guard3:1b",
"name": "llama-guard3:1b",
"digest": "494147e06bf99e10dbe67b63a07ac81c162f18ef3341aa3390007ac828571b3b",
"expires_at": "2025-10-08T14:29:39.978391-07:00",
"size": 2770397184,
"size_vram": 2770397184,
"details": {
"parent_model": "",
"format": "gguf",
"family": "llama",
"families": [
"llama"
],
"parameter_size": "1.5B",
"quantization_level": "Q8_0"
},
"context_length": null
}
]
}
},
"is_streaming": false
}
}