dstack

Control plane for agents & engineers to provision compute and run training & inference across NVIDIA, AMD, and other chips — on clouds, Kubernetes, and on-prem.

[dstack @dstackai]

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 optimization and a portable format for the result.

Deploying optimized Kimi K3 to any cloud, Kubernetes cluster, or bare-metal fleet, whether on NVIDIA, AMD, or other silicon, should be as simple as deploying a Docker image.

https://t.co/uEbTMVPLGW

[dstack @dstackai]

dstack 0.22.7 is out!

Orchestrating training or inference on Kubernetes? We keep making our Kubernetes integration more reliable and easier to configure.

This update adds automatic cleanup of orphaned resources, plus improved proxy jump reliability and configuration.

https://t.co/MuyyLARwdK

[dstack @dstackai]

dstack 0.22.7 is out!

Orchestrating training or inference on Kubernetes? We keep making our Kubernetes integration more reliable and easier to configure.

This update adds automatic cleanup of orphaned resources, plus improved proxy jump reliability and configuration.

https://t.co/MuyyLARwdK

[dstack @dstackai]

dstack 0.22.6 is out!

Long-awaited automatic detection and cleanup of orphaned instances to avoid unnecessary costs. Supported on AWS, Azure, GCP, Nebius, and RunPod, with more GPU clouds coming.

Plus improvements to Offers and Events in the UI.

https://t.co/F6yoiuyoAX

[dstack @dstackai]

AMD ❤️ dstack

An open-source, ready-to-deploy stack for running AI token factories on @AMD GPUs.

[AMD Data Center @AMDServer]

At Advancing AI 2026, @dstackai demonstrated distributed training and prefill/decode-disaggregated inference of a Qwen model on AMD Instinct MI300X GPUs.

Its open-source control plane works across GPU clouds, Kubernetes, and bare-metal clusters, letting people and agents work with the same infrastructure for development, training, and inference. More recently, dstack introduced a preview of an agent-based toolkit for optimizing inference for specific models, including Qwen3.8-27B.

Watch the dstack demo 🔽

[dstack @dstackai]

dstack 0.22.5 is out!

This release adds @lium_io as a new GPU cloud backend, supporting on-demand and spot GPUs ranging from RTX to B300.

We've also improved the UI for browsing GPU and CPU offers.

Release notes: https://t.co/zSOU8zRzBm

[dstack @dstackai]

dstack 0.22.5 is out!

This release adds @lium_io as a new GPU cloud backend, supporting on-demand and spot GPUs ranging from RTX to B300.

We've also improved the UI for browsing GPU and CPU offers.

Release notes: https://t.co/zSOU8zRzBm

[Andrey Cheptsov @andrey_cheptsov]

Biggest learning at PyTorchCon this week is that engineers are so hungry for alternatives to Slurm and Kubernetes. As soon as you mention it, you get their attention.

Super excited about the conference! Also great to see at least 5 GPU hardware vendors here. It’s the first time I’ve seen so many at such a small event. Exciting times for inference ahead!

[Andrey Cheptsov @andrey_cheptsov]

In San José tonight? Come hang out! We’re throwing a @PyTorch Conference afterparty with @CrusoeAI and the @lmsysorg SGLang

https://t.co/nyW5W3KPaf

[dstack @dstackai]

Excited to be at @PyTorch Conf in San Jose, starting tomorrow! Make sure to stop by our booth.

Come talk about training and inference on GPU clouds, K8S or on-prem, on NVIDIA, AMD or other silicon!

We're there Tue and Wed.

[Andrey Cheptsov @andrey_cheptsov]

Looking forward to @PyTorch Conf this week. Hanging out at the @dstackai booth, and Tue evening at our meetup with @CrusoeAI and @lmsysorg SGLang: https://t.co/nyW5W3KPaf

In San Jose and SF all week, happy to grab coffee.

[dstack @dstackai]

Excited to be at @PyTorch Conf in San Jose, starting tomorrow! Make sure to stop by our booth.

Come talk about training and inference on GPU clouds, K8S or on-prem, on NVIDIA, AMD or other silicon!

We're there Tue and Wed.

[dstack @dstackai]

dstack 0.22.4 is out!

This release greatly improves server stability and performance, with significantly faster offer lookups and better responsiveness under heavy workloads.

Also included: UI improvements to Launch, Offers, and project quotas in dstack Sky.

https://t.co/u4ZmYB28il

[dstack @dstackai]

@protaucol @lium_io https://t.co/VvPeW5eg2q

[dstack @dstackai]

How many coding agents can one 4xH200 node serve with Qwen3.8-Flash-Next?

With dstack presets, we tuned @lmsysorg's SGLang on Claude Code sessions: 37% lower TTFT, 74% lower p99 ITL vs the cookbook recipe.

Read about the benchmark and how preset optimization works: https://t.co/RXksAVvmF1

Huge thanks to @jarvislabsai for partnering!

[dstack @dstackai]

dstack 0.22.4 is out!

This release greatly improves server stability and performance, with significantly faster offer lookups and better responsiveness under heavy workloads.

Also included: UI improvements to Launch, Offers, and project quotas in dstack Sky.

https://t.co/u4ZmYB28il

[dstack @dstackai]

How many coding agents can one 4xH200 node serve with Qwen3.8-Flash-Next?

With dstack presets, we tuned @lmsysorg's SGLang on Claude Code sessions: 37% lower TTFT, 74% lower p99 ITL vs the cookbook recipe.

Read about the benchmark and how preset optimization works: https://t.co/RXksAVvmF1

Huge thanks to @jarvislabsai for partnering!

[Crusoe @CrusoeAI]

Open Source AI Week brings us to San Jose on Oct. 20 for AI Infra Night with @sgl_project and @dstackai.

Come meet GPU, ML, and infra engineers after the PyTorch Conference day, and request your spot early!

[dstack @dstackai]

dstack 0.22.3 is out!

You can now provision @HotAisle bare metal servers with 8x @AMD MI300X GPUs, in addition to VMs. Bare metal support is experimental.

This release also includes a number of major bug fixes and improvements. Release notes: https://t.co/j1G7JBofcW

[PyTorch @PyTorch]

Sponsor news from @CrusoeAI: We’ll be in San Jose for #PyTorchCon North America Oct 20-21.

🎤 Talks on Triton, MoE fine-tuning + model customization
🤖 Booth demos + challenges
🍻 AI Infra Night with @dstackai, @sgl_project (@lmsysorg)

Learn more: https://t.co/npmdBPB9Es
Register for AI Infra Night: 🔗 https://t.co/n0Im1qq9aL

#PyTorchFoundation

[dstack @dstackai]

dstack 0.22.3 is out!

You can now provision @HotAisle bare metal servers with 8x @AMD MI300X GPUs, in addition to VMs. Bare metal support is experimental.

This release also includes a number of major bug fixes and improvements. Release notes: https://t.co/j1G7JBofcW