Moreh and SGLang Showcase Distributed Inference System on AMD
Moreh has unveiled its distributed inference system on AMD at the AI Infra Summit 2025, showcasing collaborations with Tenstorrent and SGLang announced in a press release. The event, held in Santa Clara from September 9 to 11, featured Moreh's CEO Gangwon Jo presenting benchmark results that demonstrated the system's efficiency in optimizing deep learning models like DeepSeek, surpassing NVIDIA's performance.
Additionally, Moreh introduced a next-generation AI semiconductor system that combines its software with Tenstorrent's hardware. The company co-hosted a presentation with SGLang and organized networking sessions to further discuss their joint development of an AMD-based distributed inference system. This collaboration aims to accelerate the expansion of the deep learning inference market.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.
Also, consider following us on social media:
More from Data Centers
Sep 19 Virginia Proposes Data Center Rules and Creates AI Task Force Sep 19 House Passes Bill to Shield Ratepayers From Data Center Power Costs Sep 19 Laminar Joins L'Oreal Sustainability Accelerator Sep 19 Dnotitia Begins Testing VDPU ASIC Samples Sep 19 Nscale Files for US Initial Public OfferingSilicon Brief
Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.
Industry analysis
2025 Global Business Services Agenda: Gen AI Takes Center Stage
This industry analysis by The Hackett Group explores the transformative impact of generative artificial intelligence (Gen AI) on global business services (GBS) in 2025. The study highlights the shift from exploration to acceleration of Gen AI initiatives, with 89% of executives advancing these projects to improve customer satisfaction, innovate products, and reduce costs. The report also discusses the challenges and strategies for successful Gen AI adoption, emphasizing the need for a technology-enabled operating model and the importance of reskilling the workforce.
Read moreYou may also like
SDMC Showcases Deployable AI Home Architecture at IBC 2026
Tensordyne Details Napier AI Inference Chip and Claims One Rack Can Replace Nine
d-Matrix Raises $275 Million for AI Inference Chips
Kasm and Intel Expand Private AI Workspaces for Xeon 6
SiMa.ai and AVerMedia to Show Drone AI Hardware in Taipei
Daily AI Brief: the AI news that matters, in your inbox.