Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Baseten Delivery Network

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 2

  1. Baseten cuts GPU-resident delta weight sync time to 15 seconds

    Baseten redesigned its delta weight-sync path to use model weights already resident on GPUs as the parent copy, eliminating the need for a second full checkpoint in CPU memory. The company reports that syncing an approximately 770 GB GLM-5.3 checkpoint now takes 15 seconds with a 0.8-second request pause, versus 36 seconds and six seconds previously. Baseten also reports up to 3.2× higher output throughput per GPU at concurrency 48, while its Kimi K3 tests include an 8.4 GB delta applied across two GB300 nodes.

    Baseten Blog · 🔥 5
  2. Baseten launches BDN Sealed Volumes

    Baseten introduced BDN Sealed Volumes, a service for publishing read-only data once and mounting immutable, digest-addressed versions in deployments. Baseten says the feature can distribute model weights, checkpoints, container images, adapters, indexes, and other artifacts, with support in Baseten CLI 1.1.0 or newer and Truss 0.18.30 or newer. The announcement also says deleted versions remain restorable for seven days, while volume mounts are unavailable on T4 and L4 instances.

    Baseten Blog · 🔥 0

Experience and discussion from the community

Share my Baseten Delivery Network experienceAsk about Baseten Delivery Network

Nobody has shared their experience with Baseten Delivery Network yet.