|
- renamed the Foundation Models Catalog product to Dedicated Inference. The name change did not affect how the product works or billing.
|
|
-
added the ability to track inference service metrics using the Metrics service;
-
added new models:
You can view the current list of available models in the control panel: in the top menu, click Products → Dedicated Inference;
-
simplified the inference service cost calculation: now it is based solely on GPU consumption. Previously, the cost consisted of multiple resources: GPU, vCPU, RAM, and disk. For details, see the Dedicated Inference billing model and pricing instructions.
|
|
-
added the ability to sort configurations when creating an inference service. Now, at the configuration selection stage, you can sort them in ascending and descending order of price and performance;
-
Dedicated Inference is now available in the ru-6 pool. Also added the ability to select a location in the model catalog when creating an inference service;
-
added the ability to connect to an inference service from a private network. For details, see the Inference service connection types instructions.
|
| |
| |
|
- moved Dedicated Inference from the private preview stage to the public preview stage.
|