mirror of
https://github.com/hanzo-ml/kserve.git
synced 2026-10-30 20:53:49 +00:00
Adrian Gonzalez-MartinandGitHub
59eac45b1c
* Add ginkgo suite support to v1beta1 package * Start adding MLServer predictor spec * Add MLServer config to PredictorsConfig * Add default config for MLServer * Add defaulter * Add GetContainer method * Change comment * Add MLServer to IS spec * Remove comment * Move MLServer to SKLearn predictor * Remove other references to MLServer predictor * Use strconv instead of fmt * Add MLServer constants (to use later in XGBoost) * Add defaults for missing model-settings.json * Add SKLearn example for v1beta1 * Default model URI to models mount path * Point to Seldon's GCS to use a newer version of SKLearn * Update resource * Bump version to 0.1.2 * Add registry prefix * Fix docs * Fix a couple references on the README * Add protocol field to predictorspec * Add SKLearnV2 predictor * Default predictor to V1 protocol * Build v1 or v2 container depending on flag * Add tests for V1 * Fix image logic * Add protocolVersion flag to example * re-generate CRD * Change configmap structure for sklearn predictor * Add new structure to test overlay * Add test case for SKLearn v2 * Add missing license block * Re-generate Python SDK to add ProtocolVersions object * Fix test case for V2 * Re-generate SDK to fix wrong test
14 lines
191 B
JSON
14 lines
191 B
JSON
{
|
|
"inputs": [
|
|
{
|
|
"name": "input-0",
|
|
"shape": [2, 4],
|
|
"datatype": "FP32",
|
|
"data": [
|
|
[6.8, 2.8, 4.8, 1.4],
|
|
[6.0, 3.4, 4.5, 1.6]
|
|
]
|
|
}
|
|
]
|
|
}
|