RadixArk @radixark

🔥 Summer done right. A whole roast lamb BBQ to celebrate the good times with friends, family, builders, and our community, World Cup on the big screen (good game of Spain vs. Uruguay ⚽), smoke rolling off the grill, cold drinks in the sun, and a backyard full of great people just soaking up the vibes, that's how we enjoy the summertime! 🍢☀️🍺 Great food, great people, great times. Huge thanks to everyone who came out, and shoutout to @FishAudio for co-hosting this BBQ with us. Here's to the rest of this summer together! 🫶

keyboard_arrow_left Previous keyboard_arrow_right Next

Read more about OpenEnv community in the blog: huggingface.co/blog/openenv-a…

RadixArk is joining the OpenEnv community. OpenEnv is the protocol layer for agent environments. It standardizes how environments are published, deployed, and consumed, so developers can mix any harness, any model, any inference engine on any task. This is exactly the kind of work we care about. Democratizing frontier AI means making the full stack, training included, open and usable by anyone. Excited to join the committee alongside @PyTorch @huggingface @nvidia @Microsoft @modal @UnslothAI @reflection_ai @PrimeIntellect @mercor_ai @fleet_ai and the rest of the open source community. We will start by integrating Miles with OpenEnv and shipping end-to-end examples that people can get their hands on. And there is more to come!

Great to be at the @hud_evals hackathon @ycombinator! We met old and new friends and were really impressed by everyone working on the hard problems in “RL” (reinforcement learning and real life)! We’re always hiring ambitious, amazing people who’d love to bring frontier RL infra to everyone. Come build with us! job-boards.greenhouse.io/radixark

We're joining the party too! RL environments are very likely where the next wave of post-training progress happens. Excited to cosponsor alongside this all-star lineup. See everyone tomorrow!

hud @hud_evals

a week ago

Come join us and celebrate this weekend at HUD's Frontier/RSI RL Environments Hackathon @ the YC HQ in San Francisco. We have an all-star cast of cosponsors such as: @ycombinator, @modal, @GoogleDeepMind, @OpenAI, @AnthropicAI , @daytonaio, @FireworksAI_HQ, @MiniMax_AI,

2 0 39 16K 6

If you're at #AdvancingAI, don't miss Yusheng's (@thu_yushengsu) session on at-scale agentic RL with Miles! He'll walk through how we run RL training at scale, come hang out and ask questions! 👉 Register: amd.com/en/corporate/e…

AI at AMD @AIatAMD

2 weeks ago

1 0 5 4K 1

DFlash is a beautiful design and will be a paradigm shift for spec decoding in my opinion. Congrats @liin1211 @zhijianliu_ @modal @radixark on the release, and I’m excited to adopt DFlash for both inference and RL!

LMSYS Org @lmsysorg

2 weeks ago

🚀 New blog: The next generation of speculative decoding: DFlash and Spec V2 DFlash + Spec V2 hit >4.3X baseline throughput for LLM inference, now the default speculative decoding engine in SGLang! Together with @modal and z-lab.ai, our jointly-released DFlash

14 77 445 124K 274

With @modal and z-lab.ai, we made >4.3X throughput the new default in SGLang together. Thanks to Qiaolin Yu (@liin1211), Liangsheng Yin (@lsyincs), and Khoa Pham (@kwafam7) for landing the integration!

LMSYS Org @lmsysorg

2 weeks ago

🚀 New blog: The next generation of speculative decoding: DFlash and Spec V2 DFlash + Spec V2 hit >4.3X baseline throughput for LLM inference, now the default speculative decoding engine in SGLang! Together with @modal and z-lab.ai, our jointly-released DFlash

14 77 445 124K 274

Thanks @dstackai for this end-to-end example using Miles with dstack for RL training. Try it and let us know what you build. 👇

dstack @dstackai

a month ago

The community asked us for an example of how to use @radixark Miles with dstack for RL training. Since Miles uses Ray and dstack can run Ray, using Miles with dstack is quite straightforward. Here’s a new example of running Miles on a multi-node cluster provisioned and managed

0 4 10 5K 5

@lihanc02 @lsyincs Yes, you are absolutely right! Come and support @lsyincs

Join us in NYC on June 3rd during #NYTechWeek @Techweek_ Liangsheng Yin (@lsyincs) and Mao Cheng (@MCheng89333), both MTS at RadixArk, will present SGLang & Miles, diving into inference infrastructure for finance. RSVP: partiful.com/e/p74X9KDrgoLa…

LMSYS Org @lmsysorg

a month ago

NYC, we're bringing the inference + finance crowd together for #NYTechWeek @Techweek_! SGLang Happy Hour: AI Infra in Finance 🕤Wed, June 3 · 6–9 PM ET 📍1/2 Bond St, New York Co-hosted with @HOFCapital, @CrusoeAI, @CloudflareDev, @ArklexAI. Lightning talks from inference

0 13 33 31K 2

When @Guodzh shows up, RadixArk doesn't fold🫡 Thanks @Accel and @DecagonAI for hosting a great night, and thanks @Guodzh for representing us so well! Ready for the next round♠️

Jesse Zhang @thejessezhang

a month ago

Our first Stacked poker tournament was a huge success! 1 player representing each AI company. Congrats to: 🥇 Guodong Zhang (RadixArk, co-founder of xAI) @Guodzh 🥈 Jeremy Stribling (Cursor) 🥉 Neal Wu (Thinking Machines) @neal_wu We will be hosting another one! More below👇

keyboard_arrow_left Previous keyboard_arrow_right Next

12 13 232 55K 41

Slow, heavy environments have been the real bottleneck for agentic RL. NanoRollout tackles it head-on with a clean rollout-as-a-service design, integrated with miles for scalable agent RL. Great work from the team！

Junli Wang @JunliWang2021

2 months ago

Digital agent learning needs massive rollouts. But digital agent rollouts are painfully slow due to heavy environments. 🐌 🚀 We introduce NanoRollout, a lightweight open infra (900 lines core code) for digital agent rollout at scale, validated with three workloads: 🏋️ Large

3 40 136 36K 103

@Armanho57248840 We will be sending out platform access in waves. Please bear with us as we process everyone!

Last week, we launched the RadixArk platform for beta testing and offered $200 credits to SGLang supporters who helped spread the word. A huge thank you to everyone who signed up and reposted. The response has been incredible. We're working hard to get everyone set up, and we appreciate your patience while we work through the queue. Here's what's coming: ✅ Private Beta access rolling out in waves ✅ $200 in inference credits, pre-linked to your waitlist email Credits will be available in your account as soon as your platform invite arrives. Thanks for all the miles. Stay tuned for what comes next！

Headed to MLSys 2026? Come hang out with our friends at @RadixArk, @SGL_Project, and @EssenceVenture on Tuesday!!

Hey everyone, we hear you, and we've updated the post: x.com/radixark/statu… Our original intent was to give back to the people who supported SGLang, the contributors, the early users, the ones who believed in the project. None of this would exist without you, and this was our way of saying thank you. We're sorry for the confusion it caused. Thank you for caring enough to speak up, and we're grateful to be on this journey with you. Let's go SGLang!

RadixArk @radixark

2 months ago

We've heard the community's feedback. Our intent was to make sure the credits reached the people who supported SGLang along the way, and we couldn't be here without you. We're updating the offer to better reflect that. RadixArk's platform is open for beta, and we're offering

14 85 171 15K 35

$200 FREE CREDIT! We just launched our inference platform for beta testing, and we're giving it to the community first. ⭐ Star SGLang on GitHub (github.com/sgl-project/sg…) + repost this to claim your credits. → Limited spots, first come first serve → Deadline: May 13, 2025 (AoE) Every star, every issue filed, every PR reviewed, every question answered in Slack — You built this with us. Thank you for believing in open-source AI infrastructure, in our mission, and in us. Claim your credits: platform.radixark.com