Log inSign up
dstack
1,278 posts
@dstackai

dstack

@dstackai
Control plane for agents & engineers to provision compute and run training & inference across NVIDIA, AMD, and other chips — on clouds, Kubernetes, and on-prem.
github.com/dstackai/dstack
dstack.ai
Joined January 2020
57
Following
1,573
Followers
RepliesRepliesRepostsRepostsMediaMediaArticlesArticles

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • Pinned
    @dstackai
    dstack
    @dstackai
    Aug 20
    Inference serving is increasingly open source. But inference optimization still happens inside each provider, and the optimized deployment remains tied to its proprietary stack. This has to change. Introducing Presets: an open-source toolkit for agent-based inference
    Presets: a toolkit for agent-based inference optimization - dstack
    From dstack.ai
    1
  • @dstackai
    dstack
    @dstackai
    Aug 27
    dstack 0.21.3 is out! Presets: optimized inference configurations can now be pushed to a private registry and later deployed to any cloud, Kubernetes, or on-prem cluster. Backends: @seeweblive GPU cloud is now supported. Plus improvements to services and gateways. Release
    Release 0.21.3 · dstackai/dstack
    From github.com
  • @dstackai
    dstack
    @dstackai
    Aug 20
    Here's one example of using the presets toolkit to optimize Qwen3.8-27B on a single @AMD MI300X. Through compound learning across linked sessions and source-level patches, performance improved from 311 to 495 tok/s: +59%. The resulting preset can be deployed on any AMD cloud,
    @dstackai
    dstack
    @dstackai
    Aug 20
    Inference serving is increasingly open source. But inference optimization still happens inside each provider, and the optimized deployment remains tied to its proprietary stack. This has to change. Introducing Presets: an open-source toolkit for agent-based inference
  • @dstackai
    dstack
    @dstackai
    Aug 19
    dstack 0.21.2 is out 🚀 Distributed tasks now support node groups: one run can mix roles and hardware. Each group defines its own nodes, resources, commands, and ports, e.g. a CPU head node driving GPU workers in a single task. Also in this release: the @AMD Developer Cloud VM
    Release 0.21.2 · dstackai/dstack
    From github.com
    1
  • @dstackai
    dstack
    @dstackai
    Aug 14
    dstack 0.21.1 is out! Presets: the inference optimization agent can now patch source code (serving framework, kernels, etc). Also, sessions can be linked, so each new one starts from the previous best and pushes further. Gateways: replicas are now fault tolerant and support
    Release 0.21.1 · dstackai/dstack
    From github.com
    1