Benjamin Trent 2e8bf33b0a [ML] allow model_aliases to be used with Pytorch trained models (#91296) ... This adds model_alias support for native pytorch models. Model aliases can be used in `_infer` or within the inference processor. This way the alias can be atomically changed without down time to another deployed model. Restrictions: - Model alias changes need to be done between two models of the same kind (e.g. pytorch -> pytorch) - Model alias change is not allowed between a model that is deployed to a model that is not - Model alias change is not allowed between a model that deployed AND allocated to a model that is deployed but NOT allocated (not assigned to any nodes). - A deployment cannot be stopped (without supplying the `force` parameter) when the model has a model alias that is used by a pipeline. closes: https://github.com/elastic/elasticsearch/issues/90960		2022-11-08 08:35:33 -05:00
..
anomaly-detection	[DOCS] Clarify description of geo_results (#91237)	2022-11-04 08:15:46 -07:00
common/apis	[ML] Performance improvements for categorization jobs (#89824)	2022-09-08 18:41:01 +01:00
df-analytics/apis	[ML] Lift limit of max number of classes for classification to 100 (#89755)	2022-09-01 10:47:58 +03:00
images	[DOCS] Updates anomaly detection alert rule type screenshot. (#89532)	2022-08-23 15:37:40 +02:00
trained-models/apis	[ML] allow model_aliases to be used with Pytorch trained models (#91296)	2022-11-08 08:35:33 -05:00
ml-shared.asciidoc	[ML] add text_similarity nlp task documentation (#88994)	2022-08-02 12:17:14 -04:00