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. dstack.ai github.com/dstackai/dstack Joined January 2020-
Tweets1K
-
Followers2K
-
Following57
-
Likes1K
Going to @PyTorch Conference in San Jose next month? @CrusoeAI and we are hosting an evening on day one, October 20, 6:30 PM, right after the sessions. We're gathering GPU experts, AI researchers, AI infra engineers, and anyone into AI infra and heterogeneous AI compute. Space is limited: luma.com/6j69xyal
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 notes: github.com/dstackai/dstac…
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, Kubernetes cluster, or bare-metal fleet.
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
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/
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,
i've been saying for a while now that we need a good harness for tuning inference, but also deploying it. @dstackai has picked up the ball and done it. glad to partner with them for years now. keep up the great work.
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
@AMD @raydistributed @verl_project Node groups are documented here: dstack.ai/docs/concepts/…
Node groups are built for workloads like RL training: training jobs, inference, and sandboxes can now run side by side in one run, each on its own hardware. Here's an example that uses groups to run @raydistributed on dstack, fine-tuning an agent with RAGEN and @verl_project: dstack.ai/docs/examples/…
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 image moves to ROCm 7.14, plus a major bugfix. Full release notes 👇 github.com/dstackai/dstac…
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 in-place scaling. Plus lots of other improvements: github.com/dstackai/dstac…
Love it! Works on @tenstorrent. Go @dstackai
Super excited about this release. Most of the work went into presets. If you spend time optimizing inference, this is for you. You point the agent at a model and it figures out how to serve it best, down to patching kernels when flags aren't enough. A built preset can be
Super excited about this release. Most of the work went into presets. If you spend time optimizing inference, this is for you. You point the agent at a model and it figures out how to serve it best, down to patching kernels when flags aren't enough. A built preset can be deployed anywhere. Works on @nvidia, @AMD, and @tenstorrent, any cloud, K8S, or bare metal. dstack.ai/docs/concepts/… A longer write-up with results from our own sessions is coming soon.
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
Find the updated docs on presets at dstack.ai/docs/concepts/…. Can't wait to see what you build with them! Any feedback is very welcome. A long write-up on how presets find the optimized baseline and streamline the discovery of new kernels is coming soon!
Autoresearch is a real shift in how AI itself is built. @transformerlab just launched Primus, a service that automates the full research loop. It reads papers, forms hypotheses, writes code, runs experiments, and writes the final paper. Also great to see @dstackai helping with compute orchestration!
I am deeply proud to finally share what we’ve been building. We're calling it Primus. With a single prompt, it does the full job of a Machine Learning researcher from prompt to paper. Our goal is massive: we believe this can change the trajectory of how all scientific research
Sezer Kutluk @sezerkutluk
583 Followers 5K Following @ScuolaNormale | Prev. Scientist @LeibnizWGL, ERCIM Fellow @Fraunhofer, TeamLead @Huawei etc | AI, ML, CompVis, LLM, XAI, TrustworthyAI, learning dynamics | PhD
Agent Maison @agent_maison
3 Followers 240 Following curating AI tools that actually run. agents need computers. DMs open if you built something cool
Zakaria @zakariaornot
582 Followers 433 Following co-founder & ceo @overshootai yc w26 | prev at @meta, @uber and @mit obsessed with my three users
DGY @D363N6UY
375 Followers 6K Following
F @F_AI_F
1 Followers 112 Following
Özgür Güler @ozgurgulerx
484 Followers 505 Following LLM inference systems, GPU networking, distributed serving...
cybersecureworld @cybersecureusa
30 Followers 655 Following Cyber Security Researcher | Ethical Hacker | Bug Hunter | Securing the Digital World
PayPerQ @PPQdotAI
2K Followers 262 Following Your private way to access all of the latest and greatest AI models and tools via Bitcoin, Crypto, and credit card top-ups. Pay-per-use, no subscriptions!
amar santpur @amarsantpur
64 Followers 3K Following
infradev @infradev2
14 Followers 1K Following Interested in infrastructure development, cyber operations and security engineering
—Féachaint— @LikeErkle
545 Followers 2K Following
brrrock @bchap1n
545 Followers 2K Following powershell and llm inference struggles & shitposts | local AI open source must win | SRE @Proofpoint (opinions my own) | left wing working class voter
Chris O'Rourke @RsThrive
1K Followers 4K Following Cloudforce One R.E.A.C.T. @Cloudflare Thoughts are my own. Prior; Founder @SoteriaSecurity, @Alienvault, @Apple, @NSAgov, @USArmy
Alex Welcing @AlexWelcing
636 Followers 7K Following Building @ https://t.co/5dUr2SjUOu They are not our dogs I don’t want to live the wrong live and then die. 📺The Leftovers, Station 11, Succession
Jack Zampolin @jackzampolin
38K Followers 3K Following Local AI Infra / gents @edgeofsource 🧙♂️/ 🇺🇸🤖 https://t.co/jKYVLycmfL
Zaheeru @zaheersheriff
130 Followers 1K Following
Abhinav Prasad Yasasw... @AbhinavPY
77 Followers 2K Following Grad Student at @SCAI_ASU trying to keep up with the developments in AI.
Ganesh Chandra @GaneshChandra_
8 Followers 238 Following
Mujahed Syed @syedmujahed97
189 Followers 931 Following Applied AI @amazon | Inference Nerd | Views personal
alejandro @alejoelopez
420 Followers 354 Following Deploying AI compute to builders all over the world @highrise_ai // @hut8corp
Jaehoon Kim @jaehoonkim__
126 Followers 1K Following
P @pjl69420
0 Followers 392 Following
Sergio Soage @Sergio_Soage
1K Followers 7K Following artificial intelligence, math. Random stuff @ https://t.co/Sf3LqgedZX
Billionaire Protocol @billionaireops
156 Followers 6K Following
Ilya͇ͪ Ta̗͎ͭ̋̆... @ilyatabakh
1K Followers 3K Following Shaping Tomorrow in AI Infra & Energy | VP Innovation @TensorWave | Cohost @LiveEIR & Powering the AI Stack | Redistributing the future in KC
William Chen @solidwillity
1K Followers 7K Following trying to manufacture inference hw + sw @fdotinc @scale_at_gmi
SaaS Scale @ChiMaoaa
6 Followers 730 Following Stop letting a piece of Javascript bully your best customers behind your back. We let your backend talk like a normal human being who actually likes people."
Monish Maheswaran @sudomonish
715 Followers 1K Following research @berkeley_ai research fellow @AnthropicAI prev. @togethercompute @apple @Berkeley_EECS
Pollux9437 @Orange41324306
1K Followers 3K Following Agent @yipitdata. RL Infra and pretrain research at night, sometimes photography and poetry. writer account @orange97648. Views are my own
hualin wu @wu_hualin
8 Followers 933 Following
Aakanksha Chowdhery @achowdhery
15K Followers 8K Following @Stanford // Previously @GoogleDeepMind :: PaLM, Gemini, @reflection_ai // @MSFTResearch, @Princeton // views my own and subject to change
Rajesh Parikh @ParikhRajesh07
62 Followers 2K Following Building Infrastructure for self learning and improving AI agents
changbo @mrnetman
81 Followers 4K Following
Steven Yu @Guanqi_Yu_
5 Followers 422 Following
alejandro @alejoelopez
420 Followers 354 Following Deploying AI compute to builders all over the world @highrise_ai // @hut8corp
Vishnu - Jarvislabs.a... @vishnuvig
2K Followers 2K Following Founder - https://t.co/rmc2uywaIp Youtube - https://t.co/7UTfrP1GJt
JarvisLabsAI @jarvislabsai
2K Followers 234 Following Build, train and serve AI at scale. On-demand GPUs, serverless inference and high-speed InfiniBand clusters.
Ethan (Yusheng) Su @thu_yushengsu
783 Followers 1K Following Founding Member @radixark | Prev @AMD | Ph.D @TsinghuaNLP | Intern @Microsoft.
KVCache.AI @KVCache_AI
1K Followers 109 Following Hi, this is https://t.co/EO7MXLjjSU official account. We build systems for efficient LLM serving, including KTransformers, Mooncake and AgentENV.
LightSeek Foundation @lightseekorg
3K Followers 0 Following LightSeek is the creator of TokenSpeed, TorchSpec, and SMG — building next-generation AI infra systems https://t.co/xGPFwGC87l
Transformer Lab @transformerlab
2K Followers 166 Following Building Primus, the world’s first fully autonomous AI researcher available to everyone. https://t.co/WdcBhhEZQt
Neil Bhatt ⚡️ @_neilbhatt
350 Followers 591 Following product @ lightning ai ⚡️husband 🤵🏽♂️ dad 👶🏽 in the pursuit of being the man my puppy thinks I am 🐶
Crusoe @CrusoeAI
19K Followers 341 Following The AI factory company. We are on a mission to accelerate the abundance of energy and intelligence.
vmiss @vmiss33
14K Followers 6K Following Enterprise Architect. AI Infrastructure. Electrical Engineer. #VCDX-236 @e2eea_global. ransomware is a disaster.
RiftStack AI @CloudRiftAI
160 Followers 115 Following An inference optimization lab. We make models run faster and cheaper through compiler and serving research.
Skyler Miao @SkylerMiao7
18K Followers 160 Following Just an engineer. ex-Head of Engineering @MiniMax_AI Built MiniMax M2.x, Code, Audio & @Hailuo_AI
Kaichao You @KaichaoYou
11K Followers 151 Following Ph.D. from Tsinghua University. Core maintainer of @vllm_project . Co-Founder & Chief Scientist @Inferact .
Woosuk Kwon @woosuk_k
9K Followers 826 Following @inferact | @vllm_project | prev: PhD @Berkeley_EECS
Guitar Cat + LLM @GenAI_is_real
15K Followers 558 Following 🎸🐱🤖 Multi-Modal Research and Inference @radixark | SGLang @lmsysorg | Prev: Tsinghua BS, CMU, UCLA PhD (Quit), Amazon AGI SF Lab, ByteDance Seed
TensorWave @tensorwave
3K Followers 1K Following Empowering the next wave of AI with @AMD Instinct™ GPUs 🌊
Makora @makora_ai
576 Followers 0 Following AI-powered GPU kernel generation enabling continuous optimization and universal deployment
LMSYS Org @lmsysorg
18K Followers 204 Following Large Model Systems Organization: We developed SGLang @sgl_project (https://t.co/OjwQadINKU), Chatbot Arena (now @arena), and Vicuna!
Verda @verdacloud
1K Followers 130 Following Frontier AI Cloud Infrastructure designed for AI Builders https://t.co/kw2dI1MdQG
Ying Sheng @ying11231
19K Followers 898 Following Cofounder & CEO @radixark @lmsysorg | @sgl_project (https://t.co/6e9BrnaWXK) | 零落成泥碾作尘 只有香如故
tirth @tcv1991
295 Followers 2K Following Building something new. Accelerate American AI infrastructure 🇺🇸 Prev - @awscloud @runpod | @NYUStern
Kyle Parrish @KyleHParrish
2K Followers 1K Following investing @craft_ventures previously @figma @dropbox
Phala @PhalaNetwork
141K Followers 835 Following Empowering 10,000 builders and companies to build scalable, private, and safe intelligence.
Aleksandr Patrushev @AleksandrPatr
99 Followers 52 Following Head of Product Management - ML/AI @Nebiusai
Marvin Tong @marvin_tong
15K Followers 4K Following do things for AI privacy : Trust Machines @PhalaNetwork / Privacy LLM @redpill_gpt / 🦞 icloud for AI agent: https://t.co/4MpkGHHOhb /
Huaizheng Zhang @zhzHNN
4K Followers 766 Following Learning AGI at AI Lab. ex-founding engineer. PhD @NTUsg. Opinions are my own.
Luca Baggi @baggiponte
549 Followers 2K Following 📈 AI Engineer @ https://t.co/Du2lQ9AFgU 🗞 Ho scritto spiegoni @ilpost 🎓 MSc Econ & Stats @LaStatale 🎓 BA Filosofia @UniBergamo & @SorbonneParis1
Brandon Johnson @bj0hn5on
606 Followers 1K Following Product Tech Lead @NVIDIA | B2B Enterprise AI and Deep tech Investor
Aleks Shar (sci/acc) ... @aleks_sharik
743 Followers 3K Following Causally Curious - Make Instinct GPUs go BURR @AMD - Quantitative Models x-@intel, @datmahealth, @hpe (opinions are my own)
David Bennett @DavidBennett__
5K Followers 4K Following CEO & Co-Founder of ai&. Ex-CCO@Tenstorrent. 元社外取締役@Sanrio. 元レノボ兼NEC PC代表取締役執行役員社長. Ex-VP@Lenovo, CEO@NEC PC, CVP@AMD. Living in Austin🇺🇸なう. Ex-🇨🇦🇸🇬🇯🇵.
knarik @knarikava
2K Followers 1K Following co-founder @loudetudes l writing some sf travel recs reimagining printed travel guides, all shot on 35mm film
AI at AMD @AIatAMD
59K Followers 115 Following Advancing AI innovation together. Built with devs, for devs. Supported through an open ecosystem. Powered by AMD. #TogetherWeAdvance
Sharon Zhou @realSharonZhou
28K Followers 0 Following Recursively self-improving | VP Eng & AI @AMD | Prev: Founder/CEO, Lamini. CS Faculty & PhD @Stanford. @Harvard | @MIT 35 under 35. Angel investor.
Natik Gadzhi @natik@h... @natikgadzhi
2K Followers 1K Following Engineering leadership @LambdaAPI, open source, dev tools. Computers were a mistake. I don’t speak for my employer. Blog: https://t.co/hqx5umkAO5
Runpod @runpod
9K Followers 17 Following AI Developer Cloud. AI infrastructure developers trust. https://t.co/PWVZocfp6D
Nebius @nebiusai
40K Followers 924 Following The ultimate cloud for AI innovators. For GenAI open-source model endpoints, check out @nebiustf.You might like
