Incoming NVIDIA H100 systems ready to pick up in March

News and Updates

Innovative Leap in Cloud HPC/AI: Eliovp's New Era of Portable, High-Performance Computing Solutions

Diving Deeper: Insights from Our LLM Inference Testing part 2
February 10, 2024

Diving Deeper: Insights from Our LLM Inference Testing part 2

In our latest blog post, we delve into the enhanced performance of AMD Instinct™ MI300X accelerators for LLM inference, highlighting significant improvements in throughput efficiency and scalability following key updates to our software and hardware setup. Discover how these advancements are shaping the future of AI and machine learning in our comprehensive analysis of updated benchmarks.

Diving Deeper: Insights from Our LLM Inference Testing
February 8, 2024

Diving Deeper: Insights from Our LLM Inference Testing

This blog post explores the performance of a Supermicro server with AMD Instinct™ MI300X accelerators for Large Language Model inference, focusing on ZeRO-inference with the Bloom 176B LLM. Key findings include superior throughput efficiency and scalability in batch processing, highlighting the MI300X's potential in both inference and training tasks for AI and machine learning. The post details technical insights and benchmarks, demonstrating the server's advanced capabilities in handling complex LLM tasks.

Redefining AI Efficiency: The Power of the AMD Instinct™ MI300X in LLM Inference and Training
February 2, 2024

Redefining AI Efficiency: The Power of the AMD Instinct™ MI300X in LLM Inference and Training

The transformative potential of the AMD Instinct™ MI300X in enhancing AI efficiency, focusing on its impact on LLM inference and training. It highlights tests conducted with Supermicro servers equipped with  MI300X accelerators, highlight significant improvements in computational performance. The MI300X not only enhances throughput per token but also supports larger batch sizes without memory constraints, offering substantial benefits in AI and ML applications. This breakthrough technology sets new benchmarks for AI development, promising faster, more efficient model training and processing capabilities.

One Stop Shop
September 28, 2023

One Stop Shop

Eliovp steps into cloud HPC/AI, innovating with portable data centers, advanced AMD software optimization, and expanding projects in Belgian R&D lab.