Improved replica selector
To handle massive bursts of traffic, we've helped user scale to hundreds of replicas on model deployments. To make it easier to set minimums and maximums for large numbers of replicas, we've added...
Changelog | Page 4
See our latest feature releases, product improvements and bug fixes
Aug 14, 2024
Jul 9, 2024
Pin frequently-used models for easy access
By popular demand: you can now pin models and chains to the top of your workspace! To pin an item, click into the ... menu on any model or chain and select Pin . You can pin up to 6 items for quick...
Jul 2, 2024
Export billing usage data
You can now export your model and billing usage data for in-depth analysis in your preferred tool. The exported CSV includes all the model usage data from the selected billing period. This includes:...
Jun 11, 2024
Run model inference asynchronously on Baseten
We’re thrilled to announce that you can now run async inference on Baseten models! This unlocks some powerful inference use cases: Scalable processing: Schedule tens of thousands of inference...
Apr 22, 2024
Refreshed model overview page with deployment statuses
We’ve revised the model overview page to give you more information about model deployments at a glance. Each model card now contains: The total number of deployments. Counts for deployment statuses:...
Apr 3, 2024
Improved log filtering
You can now filter logs through the main text input. Just start typing the filter you’re looking for, like level , and autocomplete options will appear. Currently, logs filter by: Log level: zoom in...
Mar 26, 2024
Permit inference on unhealthy models
A model enters an “unhealthy” state when the deployment is active but there are runtime errors such as downtime on an external dependency. We now permit inference requests to proceed even when a...
Mar 21, 2024
Improve performance and reduce cost with fractional H100 GPUs
Baseten now offers model inference on NVIDIA H100mig GPUs, available for all customers starting at $0.08250/minute. The H100mig family of instances runs on a fractional share of an H100 GPU using...
Mar 20, 2024
Manage models with the Baseten REST API
We’re excited to share that we’ve created a REST API for managing Baseten models! Unlock powerful use cases outside of the (albeit amazing) Baseten UI - interact with your models programmatically,...
Mar 7, 2024
Configure model hardware with new resource selector
Every deployment of an ML model requires certain hardware resources — usually a GPU plus CPU cores and RAM — to run inference. We’ve made it easier to navigate the wide variety of hardware options...
