Changelog

Navigator Release Notes

• Release v2.270.1

  Release Date: May 19, 2025

  Summary

  This is the third release of our stability push, with a focus on network, webFrame, and cluster stability. We also introduce a new onboarding flow and the AI Models tab to make getting started with Navigator and deploying your first model easier and more intuitive.

  New Features

  webFrame Distribution and Metrics

  Better control and visibility into model deployment across your machines and clusters.

  Technical Details:

  • Shows memory requirements for all models
  • Displays memory availability for each machine and cluster
  • Allows selection of specific node or cluster to run the model on

  User Impact:

  • Users can more easily select which machine or cluster to deploy models to
  • Users can quickly see how much available memory they have in their cluster, and how much of their memory a model will use

  AI Models Tab

  New tab on the left hand navigation menu allowing users to select a model, learn more about it, and deploy it with one click.

  Technical Details:

  • Imports models from Hugging Face (many may require API key)
  • Creates a canvas and deploys it with one click
  • Shows technical specs and description of each model

  User Impact:

  • Easily way to find models that fit their needs, and the hardware they will be using
  • 1-click deploy - no need to create a canvas or update settings
  • New home/hub for models we add/support
  • Easy way to browse all the webAI compatible models
  • Search, filter, or sort models

  New Onboarding Screen

  New screen to get additional information at onboarding. This will be the base for adding additional customization options.

  Technical Details:

  • Captures users Name, Company Name, Role

  User Impact:

  • Allows users to give additional information so we can provide better CS and customize their in-product experience

  Improvements

  Improved Network Discovery

  New network discovery node so machines can better find each other and share information.

  User Impact:

  • Faster and more reliable connecting machines and clusters

  Improved Remote Connectivity

  Updated runtime version with more secure and reliable remote connectivity to other machines in your organization.

  User Impact:

  • Faster and more reliable inference when chatting with models on remote machines

  Additional Notes

  Many UI bugs have been fixed in this release, improving overall stability and user experience

• Release v2.246.0

  Release Date: April 9, 2025

  Summary

  Performance improvements to webFrame, and support for additional Deepseek V3 and R1 quantizations. Organizations and Remote Deployments available for select customers/prospects/users. Bug fixes and additional improvements.

  New Features

  webFrame Fixes and Additional Model Support

  Better speed performance and stability from models run on webFrame. New quantizations of Deepseek V3 and R1 available in Navigator and webFrame.

  Technical Details:

  Support for Deepseek quantization:

  • Deepseek R1 4 bit
  • Deepseek R1 Distill Llama 8B
  • Deepseek V3 4 bit

  User Impact:

  • Available in the Model Dropdown of the LLM Element
  • 4 bit quantization for V3 and R1 means users can now run either on a single mac studio or 3 mac minis (all high RAM specs, not base)
  • Deepseek R1 Distill Llama 8B can use our optimizer and needs less than 15GB of RAM

  Organizations and Remote Connectivity

  Create a team of users and share access to your clusters' resources and deployments.

  Technical Details:

  • Runtime has added a Homeport Database that allows for managing users and remote connectivity to users' Runtimes
  • Can be deployed to a local machine or to the cloud, depending on what the user wants
  • Current implementation is webAI's Homeport DB for testing purposes, but customers can't deploy their own yet
  • Teams who want to test this will need to be in sales process or current customers who want to test the alpha
  • Can only add users to teams within that Homeport DB, no connections across multiple organizations

  User Impact:

  • Users can invite anyone to their organization, and join as many organizations as they like
  • Allows users to interact with models deployed by their team regardless of what machines they are running on
  • Users can deploy flows to each other's clusters
  • Users can manage the compute resources and deployments in each other's clusters

  Improvements

  Model Changes When Using Groq API Key

  Mixtral 8x-7b-32768 was deprecated in Groq, so we replaced it with Qwen 32B for dataset generation.

  User Impact:

  • More advanced model used in Dataset Generation for Groq API Key users

  Bug Fixes

  MLX Driven Wired Memory Limits Are No Longer Enforced

  Issue: On Mac Sequoia v15.3.1, we were not able to run Deepseek v3 (352 GB) even though we had 512 GB RAM available

  Resolution:

  • This is now handled as part of MLX and does not require user intervention in the terminal

  Previously required manual commands:

  sudo sysctl iogpu.wired_limit_mb=471040

  sudo sysctl iogpu.wired_lwm_mb=471040

  User Impact: No user intervention required in the terminal

  Python Process Cleanup on Navigator Close

  Issue: Python processes related to stopped canvases would sometimes stay active after a user closes Navigator by clicking the red X-button

  Resolution: Process now cleans itself up and Navigator shuts down as expected

  User Impact: No more unexpected background Navigator processes running

Companion Release Notes

• Coming Soon