mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
b237df8f18
This PR makes setting up Ollama optional for CI. By default, we use `replay` mode for inference requests and use the stored results from the `tests/integration/recordings/` directory. Every so often, users will update tests which will need us to re-record. To do this, we check for the existence of a label `re-record-tests` on the PR. If detected, - ollama is spun up - inference mode is set to record - after the tests are done, if any new changes are detected, they are pushed back to the PR ## Test Plan This is GitHub CI. Gotta test it live.
132 lines
4 KiB
JSON
132 lines
4 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:11434/api/tags",
|
|
"headers": {},
|
|
"body": {},
|
|
"endpoint": "/api/tags",
|
|
"model": ""
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "ollama._types.ListResponse",
|
|
"__data__": {
|
|
"models": [
|
|
{
|
|
"model": "nomic-embed-text:latest",
|
|
"modified_at": "2025-07-29T16:46:26.304701-07:00",
|
|
"digest": "0a109f422b47e3a30ba2b10eca18548e944e8a23073ee3f3e947efcf3c45e59f",
|
|
"size": 274302450,
|
|
"details": {
|
|
"parent_model": "",
|
|
"format": "gguf",
|
|
"family": "nomic-bert",
|
|
"families": [
|
|
"nomic-bert"
|
|
],
|
|
"parameter_size": "137M",
|
|
"quantization_level": "F16"
|
|
}
|
|
},
|
|
{
|
|
"model": "llama-guard3:1b",
|
|
"modified_at": "2025-07-25T14:39:44.978630-07:00",
|
|
"digest": "494147e06bf99e10dbe67b63a07ac81c162f18ef3341aa3390007ac828571b3b",
|
|
"size": 1600181919,
|
|
"details": {
|
|
"parent_model": "",
|
|
"format": "gguf",
|
|
"family": "llama",
|
|
"families": [
|
|
"llama"
|
|
],
|
|
"parameter_size": "1.5B",
|
|
"quantization_level": "Q8_0"
|
|
}
|
|
},
|
|
{
|
|
"model": "all-minilm:l6-v2",
|
|
"modified_at": "2025-07-24T15:15:11.129290-07:00",
|
|
"digest": "1b226e2802dbb772b5fc32a58f103ca1804ef7501331012de126ab22f67475ef",
|
|
"size": 45960996,
|
|
"details": {
|
|
"parent_model": "",
|
|
"format": "gguf",
|
|
"family": "bert",
|
|
"families": [
|
|
"bert"
|
|
],
|
|
"parameter_size": "23M",
|
|
"quantization_level": "F16"
|
|
}
|
|
},
|
|
{
|
|
"model": "llama3.2:1b",
|
|
"modified_at": "2025-07-17T22:02:24.953208-07:00",
|
|
"digest": "baf6a787fdffd633537aa2eb51cfd54cb93ff08e28040095462bb63daf552878",
|
|
"size": 1321098329,
|
|
"details": {
|
|
"parent_model": "",
|
|
"format": "gguf",
|
|
"family": "llama",
|
|
"families": [
|
|
"llama"
|
|
],
|
|
"parameter_size": "1.2B",
|
|
"quantization_level": "Q8_0"
|
|
}
|
|
},
|
|
{
|
|
"model": "all-minilm:latest",
|
|
"modified_at": "2025-06-03T16:50:10.946583-07:00",
|
|
"digest": "1b226e2802dbb772b5fc32a58f103ca1804ef7501331012de126ab22f67475ef",
|
|
"size": 45960996,
|
|
"details": {
|
|
"parent_model": "",
|
|
"format": "gguf",
|
|
"family": "bert",
|
|
"families": [
|
|
"bert"
|
|
],
|
|
"parameter_size": "23M",
|
|
"quantization_level": "F16"
|
|
}
|
|
},
|
|
{
|
|
"model": "llama3.2:3b",
|
|
"modified_at": "2025-05-01T11:15:23.797447-07:00",
|
|
"digest": "a80c4f17acd55265feec403c7aef86be0c25983ab279d83f3bcd3abbcb5b8b72",
|
|
"size": 2019393189,
|
|
"details": {
|
|
"parent_model": "",
|
|
"format": "gguf",
|
|
"family": "llama",
|
|
"families": [
|
|
"llama"
|
|
],
|
|
"parameter_size": "3.2B",
|
|
"quantization_level": "Q4_K_M"
|
|
}
|
|
},
|
|
{
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"modified_at": "2025-04-30T15:33:48.939665-07:00",
|
|
"digest": "195a8c01d91ec3cb1e0aad4624a51f2602c51fa7d96110f8ab5a20c84081804d",
|
|
"size": 6433703586,
|
|
"details": {
|
|
"parent_model": "",
|
|
"format": "gguf",
|
|
"family": "llama",
|
|
"families": [
|
|
"llama"
|
|
],
|
|
"parameter_size": "3.2B",
|
|
"quantization_level": "F16"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|