Skip to content

Jul Patch 1

v3.1-40 Update 1

17 Jul, 2026

This update release primarily includes bug fixes and minor enhancements to existing features listed below.

Token Factory

Display URL by Modality

The API endpoint section in the model card now displays endpoint URLs dynamically based on the model’s supported modalities and API compatibility. If a model supports multiple endpoints, all applicable URLs are displayed to the user.

In the first example, the model supports chat completions, responses and messages APIs.

Chat and Other Endpoints

In the next example, the model supports APIs for image generation.

Chat and Other Endpoints

Storage Settings for Huggingface Cache Volume

Operators can now specify storage settings such as "read/write mode" and "storage class" for Huggingface cache volumes. This allows the storage volume to be used as a common model cache across multiple model deployments allowing these deployments to reuse already-downloaded model weights instead of downloading the same weights repeatedly.

In the example below, for the model deployment based on vLLM, the operator can now specify the "storage class name" and "read write mode"

PVC Settings

Compute Cluster Registration Status

The Compute Clusters page now displays the current stage of the cluster registration process, providing greater visibility into registration progress.

Supported statuses include:

  • Registration Pending – Registration has not yet started
  • Registration In Progress – Registration is underway, with visibility into services that are starting or have failed
  • Registration Completed – All required services have been successfully registered and the cluster transitions to a successful state

Cluster Registration

Bug Fixes

The following bug fixes are included in this release:

Bug ID Description
RC-51430 Fixed an issue where racks operating at 100% utilization were displayed with a Warning status. Fully utilized racks are now correctly reported as Unhealthy
RC-51425 Fixed an issue in the Rows & Racks canvas where the Zoom In, Zoom Out, Fit to Screen, and Lock controls disappeared after multiple rows were added. The controls now remain fixed and accessible within the right-side panel
RC-50843 Fixed an issue where inventory audit logs incorrectly displayed the interface as BROWSER for actions performed using an API key
RC-51311 Token Factory: Fixed an issue where the Model API Details page displayed an incorrect currency when the deployment currency was configured as USD.
RC-51580 Fixed a UI alignment issue on the Audit Logs page in the Ops Console where timestamps in the Date column overlapped with values in the User column, making both fields difficult to read
RC-51580 Fixed an issue where updating SKU sharing failed when retaining an existing tenant organization and adding another organization
RC-51518 Fixed an issue where the SKU list in the Ops Console displayed the internal SKU name instead of the user-friendly SKU display name returned by the backend.