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
Joined January 2020
- Tweets1.3K
- Following57
- Followers1.6K
- Likes1.1K
Pinned Tweet
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.
dstack.ai/blog/presets/
dstack retweeted
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.
github.com/dstackai/dstack/r…
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.
github.com/dstackai/dstack/r…
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.
github.com/dstackai/dstack/r…
AMD ❤️ dstack
An open-source, ready-to-deploy stack for running AI token factories on @AMD GPUs.
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 retweeted
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: github.com/dstackai/dstack/r…
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: github.com/dstackai/dstack/r…
dstack retweeted
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!
dstack retweeted
In San José tonight? Come hang out! We’re throwing a @PyTorch Conference afterparty with @CrusoeAI and the @lmsysorg SGLang
luma.com/6j69xyal
dstack retweeted
Looking forward to @PyTorch Conf this week. Hanging out at the @dstackai booth, and Tue evening at our meetup with @CrusoeAI and @lmsysorg SGLang: luma.com/6j69xyal
In San Jose and SF all week, happy to grab coffee.
dstack retweeted
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.
github.com/dstackai/dstack/r…
dstack retweeted
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: dstack.ai/blog/qwen38-flash-…
Huge thanks to @jarvislabsai for partnering!
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.
github.com/dstackai/dstack/r…
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: dstack.ai/blog/qwen38-flash-…
Huge thanks to @jarvislabsai for partnering!
dstack retweeted
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!
Where to find #SGLang at Open Source AI Week:
Sun Oct 18 · InclusionAI Tech Night, SF
Tue Oct 20 · SGLang x LinkedIn Meetup, Sunnyvale
Tue Oct 20 · AI Infra Night at PyTorchCon, San Jose
Links below. opensourceaiweek.com @open_intel_fdn #OpenSourceAIWeek #OpenIntelligence
1️⃣ Sun Oct 18 · InclusionAI Tech Night: Your AI Reality Check in SF, hosted by Ant Open Source and inclusionAI. Request to join: luma.com/xs9sn0lp
2️⃣ Tue Oct 20 · SGLang x LinkedIn Meetup in Sunnyvale. Talks on LLM serving, including how LinkedIn runs SGLang in production. Limited spots, request to join: luma.com/zbp6a1e1
3️⃣ Tue Oct 20 · AI Infra Night #PyTorchCon in San Jose with dstack and Crusoe. GPU and infra folks, after the conference day. Request to join: luma.com/6j69xyal
dstack retweeted
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: github.com/dstackai/dstack/r…
dstack retweeted
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: bit.ly/3TKs7bi
Register for AI Infra Night: 🔗 bit.ly/4AX0nRy
#PyTorchFoundation
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: github.com/dstackai/dstack/r…
dstack retweeted
dstack 0.22.2 is out!
You can now provision compute on @daytonaio and orchestrate training and inference with NVIDIA B300/H200 and AMD MI355X GPUs.
Presets now use cache-aware routing even without PD disaggregation.
Release notes: github.com/dstackai/dstack/r…
