🎙️ 𝗠𝗟𝘅𝗰𝗲𝗹 𝗮𝘁 𝗔𝗠𝗗 𝗔𝗱𝘃𝗮𝗻𝗰𝗶𝗻𝗴 𝗔𝗜 𝗞𝗼𝗿𝗲𝗮

On Nov 4, our CEO @inureyes presented LLM/VLM inference with MLxcel on AMD Strix Halo.

MLxcel 0.8 adds an AMD ROCm backend.
➡️ github.com/lablup/mlxcel

Thanks to @AMD for the opportunity!

#Lablup #AMD

☃️ 𝟮𝟬𝟮𝟲 𝗪𝗶𝗻𝘁𝗲𝗿 𝗜𝗻𝘁𝗲𝗿𝗻𝘀𝗵𝗶𝗽
래블업이 2026 겨울 인턴십에 함께할 분들을 찾습니다!

🔗 지원 및 상세 공고: lablup.com/ko/careers/202…

11월 3일, 래블업이 코스닥시장에 상장했습니다.

2015년, 랩(Lab)을 업(Up)시키겠다는 세 사람이 모여 래블업을 시작했습니다. 같은 꿈을 가진 사람들이 하나둘 모여 오늘에 이르렀고, 이제 전 세계 120여 개 사이트의 GPU 인프라가 Backend.AI 위에서 운영되고 있습니다.

래블업의 모토는 ‘Make AI Accessible’입니다. AI가 누구에게나 닿는 내일을 위해, 복잡한 AI 인프라를 소프트웨어로 풀어내는 래블업의 여정은 지금부터가 시작이라고 생각합니다.

래블업이 걸어갈 다음 여정에도 많은 관심과 응원 부탁드립니다.

#Lablup #MakeAIAccessible

We have been a @CloudNativeFdn Silver Member since 2020. This is our third year as a Silver Sponsor at @KubeCon_ + CloudNativeCon North America. Find us at Booth 216 in Salt Lake City, Nov 9-12.

#Lablup #BackendDOTAI #KubeCon

On Nov 4 at @AMD AI DevDay Seoul, our CEO @inureyes will talk about LLM/VLM inference on AMD Strix Halo with MLxcel, our Rust-native engine.

He'll cover memory bandwidth, continuous batching, and speculative decoding.

bnd.ai/3l8Rl
#Lablup #AMD

Lablup will be at AMD Advancing AI + AI DevDay Seoul 2026, a free AI developer event on Nov 4.

Our CEO @inureyes, an AMD Featured Speaker, will speak on LLM/VLM inference with MLxcel, our open-source engine.

#Lablup #AMD

🔗 bnd.ai/sPZ21

At HPE Partner Day, Jongmin Kim, GTM Lead at Lablup, traced Lablup's path from AI infrastructure to the token factory.

Thanks to HPE for hosting!
#Lablup #Continuum

That's a wrap on #PyTorchCon North America 2026!

Thanks to everyone who visited Booth 12!

We've long benefited from the PyTorch ecosystem, and as a PyTorch Foundation Silver Member since September, we plan to support it more actively.

#Lablup #BackendDotAI

We joined KT's K-PATH 2026 as an alumni company and KT partner!

At our booth, CEO @inureyes walked visitors through GPU utilization in Backend.AI and request flow and latency in Continuum Hub. Backend.AI supports KT Enterprise's K GPUaaS. #Lablup

#PyTorchCon Day 1 is done!

Our Booth 12 demo theme is Vertical AI. Backend.AI runs models on accelerator hardware, and Continuum tracks tokens and controls requests. AI:GO is the client, from chat to Squad.

Find us through Oct 21, local time 🇺🇸

Our CRO spoke at UCLIX Tech Seminar 2026 on optimizing GPU resources, making the case that hardware sets peak performance while software determines peak efficiency.

Thanks to UCLIX for hosting!
#Lablup #BackendDotAI

Our CEO @inureyes is on THE AI 30, MIT Technology Review Korea's list of people changing the future of AI in Korea.

AI sovereignty needs more than a model: it needs the infrastructure and software to run it. That's what we build.

🔗 technologyreview.kr/?p=52308

📣 𝗟𝗮𝗯𝗹𝘂𝗽 𝗖𝗼𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝟮𝟬𝟮𝟲 𝘁𝗮𝗹𝗸𝘀 𝗮𝗿𝗲 𝗻𝗼𝘄 𝗼𝗻 𝗬𝗼𝘂𝗧𝘂𝗯𝗲

Thanks to everyone who joined lab | up > /conf/6!

The keynote, panel talk, and session recordings are now on YouTube with English subtitles.

▶️ bnd.ai/lablupconf6-pl…

Lablup joins the @intel GPU D-series partner ecosystem, announced at #OCPSummit 2026.

Backend.AI runs NVIDIA, AMD, and Intel GPUs alongside NPUs on one platform. We plan to help enterprises bring the D-series into their existing infrastructure.

#Lablup

We joined the PyTorch Foundation as a Silver Member in September. Now we're sponsoring #PyTorchCon in San Jose!

A model built in PyTorch still needs hardware to run on. It shouldn't have to come from one vendor.

Find us at Booth 12, Oct 20-21🚀

#Lablup #BackendDOTAI

AI Festa 26 is a wrap!

Over three days in Seoul, we met companies and individuals across Korea's AI industry and talked about AI:GO, Backend.AI, and Continuum.

Thanks to everyone who stopped by Booth K-04 at COEX🙌

#Lablup #AIFesta2026

all-smi, our open-source accelerator monitoring tool, is now an official Homebrew package!

No tap needed: brew install all-smi

Think nvidia-smi, but for NVIDIA, AMD, Apple Silicon, Intel Gaudi, Google TPU, and more in one view.
🔗 github.com/lablup/all-smi

#Lablup #BackendDOTAI

Meet us at #AIFesta26 in Seoul, Oct 6-8!

We will introduce Backend.AI, which raises GPU utilization across enterprise AI infrastructure, and Continuum, our control plane for enterprise AI TokenOps.

Visit Booth K-04, COEX Hall C!
#Lablup #BackendDOTAI

🇸🇬 Tech Week Singapore 2026 is a wrap!

We introduced Backend.AI and Continuum to many visitors.

Singapore is an important part of Asia's next-gen AI infrastructure growth, so this was a meaningful milestone for us.

Thanks to everyone who stopped by!