mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-25 09:05:37 +00:00
79bed44b04
Propagate test IDs from client to server via HTTP headers to maintain proper test isolation when running with server-based stack configs. Without this, recorded/replayed inference requests in server mode would leak across tests. Changes: - Patch client _prepare_request to inject test ID into provider data header - Sync test context from provider data on server side before storage operations - Set LLAMA_STACK_TEST_STACK_CONFIG_TYPE env var based on stack config - Configure console width for cleaner log output in CI - Add SQLITE_STORE_DIR temp directory for test data isolation
57 lines
1.7 KiB
JSON
Generated
57 lines
1.7 KiB
JSON
Generated
{
|
|
"test_id": "tests/integration/inference/test_openai_completion.py::test_openai_completion_stop_sequence[txt=ollama/llama3.2:3b-instruct-fp16-inference:completion:stop_sequence]",
|
|
"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",
|
|
"name": "llama3.2:3b",
|
|
"digest": "a80c4f17acd55265feec403c7aef86be0c25983ab279d83f3bcd3abbcb5b8b72",
|
|
"expires_at": "2025-10-08T16:14:05.423042-07:00",
|
|
"size": 3367856128,
|
|
"size_vram": 3367856128,
|
|
"details": {
|
|
"parent_model": "",
|
|
"format": "gguf",
|
|
"family": "llama",
|
|
"families": [
|
|
"llama"
|
|
],
|
|
"parameter_size": "3.2B",
|
|
"quantization_level": "Q4_K_M"
|
|
}
|
|
},
|
|
{
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"name": "llama3.2:3b-instruct-fp16",
|
|
"digest": "195a8c01d91ec3cb1e0aad4624a51f2602c51fa7d96110f8ab5a20c84081804d",
|
|
"expires_at": "2025-10-08T11:35:03.108973-07:00",
|
|
"size": 7919570944,
|
|
"size_vram": 7919570944,
|
|
"details": {
|
|
"parent_model": "",
|
|
"format": "gguf",
|
|
"family": "llama",
|
|
"families": [
|
|
"llama"
|
|
],
|
|
"parameter_size": "3.2B",
|
|
"quantization_level": "F16"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|