Missed our latest SDK 2025.3.0 release? We’re making #furiousprogress unlocking new levels of performance and efficiency for large-scale models and agentic AI on RNGD. 📑 More details: furiosa.ai/blog/furiosa... 📋 Release notes: developer.furiosa.ai/latest/en/wh...

It’s been an exciting few days at #SDEC2025 ⚡ Thank you to everyone who visited our booth and joined our keynote and panel on Furiosa’s journey to building next-gen AI chips. Drop by Booth 6307 today and tomorrow as the conference continues to meet the team and keep the conversation going.

We’re pleased to announce a new partnership between FuriosaAI and ByteBridge to advance next-generation AI infrastructure across the APAC region.

🛬 We’re headed to #SDEC2025 in Kuala Lumpur next week to explore the future of AI and semiconductors. 👀 Don’t miss our co-founder and CEO, June Paik, onstage October 10 as he shares how Furiosa is building next-gen AI chips for a more sustainable future.

Introducing Furiosa NXT RNGD Server 🚀 Engineered for efficient AI inference, the NXT RNGD Server hosts up to 8 RNGD accelerators, delivering: ⚡ 4 PFLOPS (FP8) compute 📦 384GB HBM + 12TB/s bandwidth 🔋 Just 3kW power draw (compared to 10.2kW for H100 SXM servers)

Last week, we demoed OpenAI’s open-weight gpt-oss 120B model running live on RNGD, our flagship AI accelerator. Here’s a recording of the demo in action, showing that cutting-edge models can be deployed well within the existing power budgets of typical data centers:

Today we partnered with OpenAI for the grand opening of its new Seoul office, where we showcased its new open-source gpt-oss 120B model running live on RNGD. We demonstrated a real-time chatbot efficiently running the model on just two RNGD cards, using MXFP4 precision: furiosa.ai/blog/furiosa...

Day 1 at #AIInfraSummit was energizing. The conversations at our booth make it clear: the future of AI depends not just on smarter models, but on more efficient compute. That’s why we were excited to have Alex Liu onstage sharing how we are redefining performance and efficiency in AI infrastructure.

🛬 Next week, we’re at #AIInfraSummit. 👀 Watch our SVP of Product and Business, Alex Liu, present on the Enterprise AI stage at 4:10 PM on September 9. 🤝 Connect with us in the app, stop by Booth 728 from September 9 to September 11, and book a meeting in advance: lp.furiosa.ai/ai-infra-sum...

Our engineers tackle groundbreaking challenges head-on. This month, we feature Seung Ho Song, a key engineer on our compiler team, and ask him about his experience. Read the full spotlight in our newsletter: www.linkedin.com/pulse/furios...

The annual Hot Chips conference this week reminded us to share our article from the recent special issue of IEEE Micro, which highlights our Hot Chips 2024 presentation as one of the best at the event. 👀 Read the full article here: dxttx52ei7rol.cloudfront.net/Micro_202503...

🔥 From our LG AI Research news to our $125 million funding raise, and from new executive hires to presenting six papers at ICML and ACL, it’s been a busy few months. We also attended events in Singapore, Paris, and NYC. Read our latest newsletter for details. 🗞️ www.linkedin.com/pulse/furios...

Last month, we presented four papers at ICML 2025 in Vancouver and two papers at ACL 2025 in Vienna. These six papers dig into ways to make advanced AI systems more efficient, more capable, and more flexible.

At OCP APAC last week and at OCP Korea this week, we presented “From Silicon to AI Serving: Optimizing Inference and Engineering What’s Next”, which covered everything from designing and manufacturing silicon to applying it to real-world AI services.

Thank you to everyone in the AI community we met in NYC this summer and those who came to our happy hour at @nyu.edu’s Global AI Frontier Lab last week.

Last week, we presented two papers at ACL in Vienna, authored by our engineers and researchers, with collaborators from Seoul National University, @uwmadison.bsky.social, Berkeley Artificial Intelligence Research, @berkeleylab.lbl.gov, and @ucberkeleyofficial.bsky.social:

If you’re in NYC on Friday, come listen to FuriosaAI co-founder and CEO June Paik and Professor of Computer Science and Data Science KyungHyun Cho speak at our inaugural Powered by Furiosa happy hour, moderated by Associate Professor and Furiosa Advisor Nuno Lopes:

We’re thrilled to welcome Jeehoon Kang as our Chief Research Officer and Youngjin Cho as our Vice President of Hardware. 💼 Check out our open roles: furiosa.ai/jobs

We're proud to announce that we've raised $125M in Series C bridge funding to scale sustainable AI compute and accelerate our roadmap. This brings our total funding to $246 million and will help us meet growing demand from global enterprise customers for our flagship AI chip, RNGD.

🛬 Next week, we’re hosting our inaugural happy hour: Powered by Furiosa. 🍹 On August 8, we’re bringing together industry leaders and practitioners at the forefront of AI to discuss, share knowledge, and enjoy great food and drinks.

We are excited to announce that LG AI Research has adopted our RNGD AI accelerator for inference computing with its EXAONE models. RNGD achieves 2.25x better LLM inference performance per watt vs. GPUs while also meeting LG’s demanding latency and throughput requirements: furiosa.ai/blog/lg-ai-r...

This week, we presented four papers at ICML in Vancouver, authored by our engineers and researchers, with collaborators from Korea University, @ucberkeleyofficial.bsky.social, @uwmadison.bsky.social, Seoul National University, and @microsoft.com:

“Because there’s effectively no runtime, the runtime overhead converges to almost 0. That’s why we can get good results in terms of TPS/W.” -- Sol Kim, Software Engineer, Furiosa At the @pytorch.org KR Conference, Kim presented "A journey from TCP architecture to production-level LLMs."

Thank you to everyone who stopped by our RAISE Summit booth, watched our keynote, and drove the conversation on AI inference. 🤝 Couldn’t make it to #RaiseSummit or want to follow up? Reach out and let’s keep the conversation going: furiosa.ai/contact

We are excited to partner with turnkey AI cloud platform hosted·ai to deliver high-performance AI infrastructure built on our Tensor Contraction Processor (TCP) architecture. We expect hosted·ai’s cloud platform to support our flagship RNGD (pronounced “Renegade”) chip by the end of 2025.

🛬 Next week, we’re at RAISE Summit. 👀 Watch our co-founder and CEO, June Paik, keynote the Grace Hopper stage at 9:40 on July 9. 🤝 Connect with us in the #raisesummit app, stop by Booth 85 from 9:00 to 18:00 on July 8 and July 9, and book a meeting: furiosa-242397185.hs-sites-na2.com/raise-2025

📣 “It’s not healthy that there is just one architecture and just one direction,” our co-founder and CEO, June Paik, said at SuperAI last month. “We call AI the age of discovery. I think on the compute side, we need the same approach. We need to explore new architectures.”

We’re speaking at RAISE Summit in two weeks. Will you be there? Book a meeting with us for July 8 or July 9: furiosa-242397185.hs-sites-na2.com/raise-2025 And onstage, watch our co-founder and CEO, June Paik, detail Furiosa's Tensor Contraction Processor and streamlined software stack.

Our engineers are the heart and soul of the company. This month, we feature Kevin Galim, the first non-South Korean developer to join the company, and ask him about his experience. Read the full Q&A here at the end of our newsletter: www.linkedin.com/pulse/furios...

Thank you to everyone who stopped by our SuperAI booth, watched our panel and keynote, and drove the conversation on how best to power AI. 🤝 Couldn’t make it to #SuperAI 2025 or want to follow up? Reach out and let’s keep the conversation going.

🛬 This week, we’re in Singapore for #SuperAI. 👀 Watch our co-founder and CEO, June Paik, take the stage on June 18 at 11:15am and 5:40pm. 🤝 Book a meeting with us using SuperAI’s app and stop by our booth, MB2, anytime from 7:30 to 18:00: www.superai.com/mobile-app

See what’s new in our latest SDK release, check out our ICML- and ACL-accepted papers, and come see us in person at SuperAI in Singapore, Raise Summit in Paris, and at the NYU’s Global AI Frontier Lab in NYC. Our latest newsletter has all the details and links 🗞️ www.linkedin.com/pulse/furios...

We have taken the first steps to open source our Cloud Native Toolkit. Our team has been working to simplify integrating and managing Furiosa NPUs within Kubernetes and the broader container ecosystem. #FuriosaAI #CloudNative #Kubernetes #Container #Opensource

We’re speaking at SuperAI in two weeks. Stop by our booth, MB2, from 7:30 to 18:00 on June 18 and June 19. Onstage, watch our founder and CEO, June Paik, detail how Furiosa's Tensor Contraction Processor and software stack is reshaping LLM and multimodal inference for organizations globally.

🚀 Our software team has released Furiosa SDK 2025.2.0. This release brings significant new functionality to RNGD, our flagship chip for power-efficient inference on LLMs and agentic AI. 📑More details: furiosa.ai/blog/furiosa... 📋Release notes: developer.furiosa.ai/latest/en/wh...

FuriosaAI is heading to NYC🗽 🎓 From May 27 to August 15, Furiosa will be working from the Global AI Frontier Lab at @New York University. We are looking forward to meeting and collaborating with cutting edge AI companies and researchers in New York. If that's you, please reach out.

hello, world