ASUS Business’ Post

AI accelerator tinybox pro goes up for preorder for $40,000 — the device features eight RTX 4090s and two AMD Genoa EPYC processors - Tom's Hardware: AI accelerator tinybox pro goes up for preorder for $40,000 — the device features eight RTX 4090s and two AMD Genoa EPYC processors  Tom's Hardware http://dlvr.it/TGB9P4 #ai #artificialintelligence

X-Labs just released IP-Adapter checkpoint for FLUX.1-dev model by Black Forest Labs. I have decided to test it in ComfyUI. The results were incredible but my computer suffered. 😅 Hardware Specs: CPU: Intel Core i7-13700KF 3.40 GHz GPU: Nvidia GeForce RTX 3070Ti 8GB VRAM MEM: 32GB Diffusion Model: flux1-dev-fp8 Weight_dtype: fp8_e4m3fn Clip: t5xxl_fp8_e4m3fn Prompt: "holding sign with glowing green text "X-LABS IP Adapter" Resolution: 1024x1024 XLabs Sampler: 10 steps | Execution Time: 16 minutes XLabs Sampler: 25 steps | Execution Time: 40 minutes XLabs Sampler: 50 steps | Execution Time: 93 minutes #ai #generativeai #genai #generative_ai #digital_art #flux #comfyui #machinelearning

New article on #gpu acceleration featuring D2S, Inc. CEO Aki Fujimura, saying "The prevailing method in #semiconductor mask making is largely based on the traditional Manhattan style, but there’s a consensus that a shift toward #curvilinear mask making is on the horizon. This transition is likely to necessitate the use of GPUs, given their superior processing power and capability to handle complex calculations. " https://lnkd.in/eFK5s6vs

Do you like to know how to run #Opensource #llm models out of the box on AMD hardware? 👉 Do not miss the talk from my colleagues Guruprasad MP and Ryan Radjabi in Cannes next week on the WAICF Demo Stage 2! 📅 Feb. 9 ⏰ 14:30 – 15:00 Hugging Face and AMD : LLMs out of the box acceleration Abstract: Hugging Face is the default location for Opensource AI models these days. Hugging Face and AMD have been collaborating over last several months to enable all the models on Hugging Face to work out of the box on AMD platforms. In this talk you will get a glimpse of the ease of use, performance optimizations and some performance benchmarks of LLMs on AMD GPUs and also witness how easy it is to download a LLM model and execute it locally on a Ryzen ™AI laptop without internet connectivity. 👉 We have several Demos at out booth and looking forward talking to you! Ping me via WAICF app or on LinkedIn for setting up a time! #ai #ml #llm #opensource #Cannes #WAICF WAICF - World AI Cannes Festival Hugging Face #artificialintelligence #laptop #ryzen #gpu Hugging Face 

'The pivotal factor in advancing virtual production technology lies in selecting robust workstations and the introduction of ST2110 IP image distribution backbone' Find out more about ASUS's #virtualproduction tech demo that featured #GlassboxTech, Kingston Technology, AMD, LUSTER LightTech Co., Ltd., and #UnrealEngine’s latest procedurally generated content framework to deliver highly realistic, #realtime, #latencyfree virtual environments ready for feature film https://lnkd.in/gQVTN64E

Ready to take your productions to the next level? Explore Ventuz 7's Multi-GPU support. Say goodbye to limitations and hello to the endless possibilities of Ventuz 7, which allows you to run entire productions from a single workstation. 💡 No more constraints from Nvidia Mosaic or AMD Eyefinity. Arrange screens however you desire, regardless of resolution, pixel pitch, or orientation. With Ventuz 7, each physical GPU output can be treated individually, giving you the freedom to tailor displays to fit your unique production needs. But it doesn't stop there! Imagine the potential when machines with multiple GPUs are clustered together, unleashing their combined power to play out content on even larger screens or more displays. 👉 Achieve more with less hardware, saving valuable rack space while maximizing output. Check out our slideshow for a glimpse of what's possible and dive into the user manual for a deeper understanding of this game-changing feature: https://lnkd.in/eWriBDck Changing Your Perspective in Real-Time 🧡 #Ventuz #Ventuz20Years #MultiGPU #Innovation #Rendering

Transforming #healthcare through technological empowerment. Advantech Intelligent Healthcare offers the industry's first NVIDIA-Certified medical-grade computer aimed at providing AI at the edge for #hospital applications and #healthcare environments. This innovative Edge AI platform features support for the NVIDIA RTX -A6000 graphics card and NVIDIA's AI tools and frameworks such as RAPIDS, Tensor RT and Triton Inference Server. The #USM-300 from Advantech Intelligent Healthcare efficiently utilises both an NVIDIA graphics card plus video capture cards to enable the capture of large video data while executing real-time AI algorithms and analysis.

#FluidX3D v2.19 on #Intel Xeon 6 enables #CFD simulations like you've never seen before. 42.7 Billion cells on only two Xeon 6 6979P CPUs, surpassing previous 32-GPU record? Piece of cake! 🖖😎 #Xeon 6 with MRDIMMs brings a new era of #HPC, where the memory capacity of a computer is measured in TeraByte, not GigaByte, with the massive 1.7TB/s memory bandwidth to back that up. Now such super large simulations are feasible on a single compact, energy-efficient CPU server, without having to change a single line of code thanks to #OpenCL. No #GPUs required! More to follow at #SC24!! 🖖😋🟦 The FluidX3D v2.19 update is out on #GitHub - for free - adding Catmull-Rom splines for smooth camera movement and other improvements: 👉 https://lnkd.in/d9rN8qkA Thank you so much Cody V. for this incredible collaboration! Looking forward to seeing you and the team in Atlanta! 💪 https://lnkd.in/du2rHVyy

🏎️⚡️Benchmarking Llama 3.1 405B on 8x AMD MI300X GPUs We've compared how fast Llama 3.1 405B works using 8x AMD MI300X GPUs across vLLM and TGI backends. See how these setups stack up across different use cases, supported by Hot Aisle Inc. 🔥 More on the full post 🔗 https://lnkd.in/g7dVtKq2

AMD Radeon RX 7900 XTX Video Card - Thoughts on performance and stability (Fast Review)