Skip to main content
​
Week of September 28

​
New features

Page through MCP logs. get_persisted_logs now returns stored logs one small page at a time, newest first. Pass the returned next_before_id as before_id to fetch older entries. MCP log tools also cap output at 500 lines, so large logs return quickly instead of timing out. See Paging through persisted logs.

​
Updates

Send your MCP key in a request header. Remote MCP clients now authenticate with an X-API-Key or Authorization: Bearer header on every request. If you also pass a key in the URL, the header wins. Remote requests without a key no longer run under a shared server key, so each request acts only on your account. See MCP setup.

​
Bug fixes

  • Base-model deploys from the dashboard work again. Deploying a preset from Models no longer fails right away with “Extra inputs are not permitted”. Models without a supported launch preset now show a clear message before you submit. See Deploy a model.
  • No duplicate GPUs from scheduled starts. A scheduled start or automatic restart no longer leaves extra GPU instances running when a machine fails to start. See Managing a deployment.
  • Failed deployments release their GPU. Valkyrie now finds and shuts down GPU instances left running after a deployment fails.
  • Balance checks cover every running GPU. A deployment that leaves the Running state while still holding a GPU is now included in Valkyrie’s spending checks. See Quota & billing.
​
Week of September 21

​
New features

Valkyrie is live at valkyrieapp.azumo.com. Sign in to the dashboard at valkyrieapp.azumo.com. Organizations that run a separate environment can keep using their own Valkyrie URL. See the dashboard overview.Non-guessable default URL for every deployment. Each deployment is now reachable at a default URL based on a random public ID, not a sequential number. You can call your model as soon as it’s ready, without creating an alias. See Call your deployment.

​
Updates

Aliases are optional. An alias is now an optional, memorable name you add on top of a deployment’s default URL. You can set one when you deploy or add it later. Use Manage aliases on a model’s detail screen to jump to Aliases with that deployment preselected. You can also re-point an alias to a new deployment at any time. See Aliases.Search and sort across all models. On the Models screen, name search and column sorting (Model, Framework, Status, Created) now cover your whole list, not just the current page. See Models.Clearer fine-tuning statuses. Fine-tuning jobs now show Queued, Initializing, Running, Finalizing, Completed, or Failed. Initializing covers GPU start-up, model download, and dataset prep. Finalizing means the job is saving and uploading its outputs. See Track progress.