Reduces HBM Costs with GPU–Tenstorrent Heterogeneous Distributed Serving
First unveiled at Tenstorrent’s launch event, TT-Deploy, in San Francisco on May 1

SANTA CLARA, Calif., May 2, 2026 /PRNewswire/ — Moreh, an AI infrastructure software company, led by CEO Gangwon Jo, announced that it has successfully validated LLM inference performance on the Tenstorrent Galaxy Wormhole system using its proprietary ‘MoAI Inference Framework.’

Based on tests across leading Mixture-of-Experts (MoE) models—including GPT-OSS, Qwen, GLM, and DeepSeek—Moreh achieved LLM inference performance on Tenstorrent Galaxy Wormhole matching or surpassing NVIDIA DGX A100-class systems, demonstrating a compelling alternative to conventional GPU-centric AI infrastructure.

Moreh also improved cost efficiency by implementing a disaggregated serving architecture that combines GPUs with Tenstorrent Wormhole chips. By utilizing Tenstorrent processors as dedicated prefill accelerators, the company reduced reliance on high-cost HBM and lowered overall infrastructure costs.

The results were first unveiled at Tenstorrent’s launch event, TT-Deploy, held on May 1 in San Francisco.

As a strategic partner of Tenstorrent and a major external contributor to Metalium, Moreh showcased a live LLM inference demo at the event. Building on its experience operating AMD GPU-based production environments in real-world data centers, the company presented its latest technical achievements in ‘Production-Ready LLM Inference on Tenstorrent Galaxy.’

MoAI Inference Framework is a disaggregated inference solution that enables unified operation of heterogeneous GPUs and NPUs—including NVIDIA, AMD, and Tenstorrent—within a single cluster. This allows enterprises to build flexible AI infrastructure strategies without vendor lock-in.

Moreh CEO Gangwon Jo stated, “Achieving production-grade LLM inference performance and stability on Tenstorrent-based systems marks a significant milestone,” and added, “We will continue to enhance performance through deeper optimization across heterogeneous architectures and closer integration with Tenstorrent NPUs.”

Moreh is developing its own core AI infrastructure engine and, through its foundation LLM subsidiary Motif Technologies, is building end-to-end capabilities spanning both infrastructure and model domains. Simultaneously, the company is making its mark in the global market through collaborations with key partners such as AMD, Tenstorrent, and SGLang.

Reduces HBM Costs with GPU–Tenstorrent Heterogeneous Distributed Serving
First unveiled at Tenstorrent’s launch event, TT-Deploy, in San Francisco on May 1

SANTA CLARA, Calif., May 2, 2026 /PRNewswire/ — Moreh, an AI infrastructure software company, led by CEO Gangwon Jo, announced that it has successfully validated LLM inference performance on the Tenstorrent Galaxy Wormhole system using its proprietary ‘MoAI Inference Framework.’

Based on tests across leading Mixture-of-Experts (MoE) models—including GPT-OSS, Qwen, GLM, and DeepSeek—Moreh achieved LLM inference performance on Tenstorrent Galaxy Wormhole matching or surpassing NVIDIA DGX A100-class systems, demonstrating a compelling alternative to conventional GPU-centric AI infrastructure.

Moreh also improved cost efficiency by implementing a disaggregated serving architecture that combines GPUs with Tenstorrent Wormhole chips. By utilizing Tenstorrent processors as dedicated prefill accelerators, the company reduced reliance on high-cost HBM and lowered overall infrastructure costs.

The results were first unveiled at Tenstorrent’s launch event, TT-Deploy, held on May 1 in San Francisco.

As a strategic partner of Tenstorrent and a major external contributor to Metalium, Moreh showcased a live LLM inference demo at the event. Building on its experience operating AMD GPU-based production environments in real-world data centers, the company presented its latest technical achievements in ‘Production-Ready LLM Inference on Tenstorrent Galaxy.’

MoAI Inference Framework is a disaggregated inference solution that enables unified operation of heterogeneous GPUs and NPUs—including NVIDIA, AMD, and Tenstorrent—within a single cluster. This allows enterprises to build flexible AI infrastructure strategies without vendor lock-in.

Moreh CEO Gangwon Jo stated, “Achieving production-grade LLM inference performance and stability on Tenstorrent-based systems marks a significant milestone,” and added, “We will continue to enhance performance through deeper optimization across heterogeneous architectures and closer integration with Tenstorrent NPUs.”

Moreh is developing its own core AI infrastructure engine and, through its foundation LLM subsidiary Motif Technologies, is building end-to-end capabilities spanning both infrastructure and model domains. Simultaneously, the company is making its mark in the global market through collaborations with key partners such as AMD, Tenstorrent, and SGLang.

Reduces HBM Costs with GPU–Tenstorrent Heterogeneous Distributed Serving
First unveiled at Tenstorrent’s launch event, TT-Deploy, in San Francisco on May 1

SANTA CLARA, Calif., May 2, 2026 /PRNewswire/ — Moreh, an AI infrastructure software company, led by CEO Gangwon Jo, announced that it has successfully validated LLM inference performance on the Tenstorrent Galaxy Wormhole system using its proprietary ‘MoAI Inference Framework.’

Based on tests across leading Mixture-of-Experts (MoE) models—including GPT-OSS, Qwen, GLM, and DeepSeek—Moreh achieved LLM inference performance on Tenstorrent Galaxy Wormhole matching or surpassing NVIDIA DGX A100-class systems, demonstrating a compelling alternative to conventional GPU-centric AI infrastructure.

Moreh also improved cost efficiency by implementing a disaggregated serving architecture that combines GPUs with Tenstorrent Wormhole chips. By utilizing Tenstorrent processors as dedicated prefill accelerators, the company reduced reliance on high-cost HBM and lowered overall infrastructure costs.

The results were first unveiled at Tenstorrent’s launch event, TT-Deploy, held on May 1 in San Francisco.

As a strategic partner of Tenstorrent and a major external contributor to Metalium, Moreh showcased a live LLM inference demo at the event. Building on its experience operating AMD GPU-based production environments in real-world data centers, the company presented its latest technical achievements in ‘Production-Ready LLM Inference on Tenstorrent Galaxy.’

MoAI Inference Framework is a disaggregated inference solution that enables unified operation of heterogeneous GPUs and NPUs—including NVIDIA, AMD, and Tenstorrent—within a single cluster. This allows enterprises to build flexible AI infrastructure strategies without vendor lock-in.

Moreh CEO Gangwon Jo stated, “Achieving production-grade LLM inference performance and stability on Tenstorrent-based systems marks a significant milestone,” and added, “We will continue to enhance performance through deeper optimization across heterogeneous architectures and closer integration with Tenstorrent NPUs.”

Moreh is developing its own core AI infrastructure engine and, through its foundation LLM subsidiary Motif Technologies, is building end-to-end capabilities spanning both infrastructure and model domains. Simultaneously, the company is making its mark in the global market through collaborations with key partners such as AMD, Tenstorrent, and SGLang.

DONGGUAN, China, May 2, 2026 /PRNewswire/ — City University of Hong Kong (Dongguan) held its 2026 Campus Open Day on 1 May, attracting more than 50,000 online and offline visitors, and showcasing its academic strengths, facilities and student-centred learning environment.

Held at main and parallel venues, the Open Day featured university introduction, programme briefings, consultations, student sharing, public lectures and immersive activities.

In his opening address, Professor Lu Chun, Executive President of CityUHK (Dongguan), highlighted the University’s first master’s graduates’ achievements. He noted that the outstanding 2026 graduates demonstrated strong academics, cutting-edge tech mastery and practical experience from top enterprises, with the University aiming to nurture versatile talents for the AI era.

Professor Julie Juan LI, Vice President (Academic) of CityUHK (Dongguan), stated that CityUHK (Dongguan) inherits the world-class academic strengths of CityUHK, which is ranked 63rd globally and 7th in Asia in the 2026 QS World University Rankings, and has been named the “World’s Most International University” by THE for three consecutive years. She underlined the University’s full alignment with CityUHK’s academic standards and resources, sustaining consistent educational excellence through cross-campus collaboration.

In her speech, Ms Yin Rongrong, Director of the Admissions Office, noted that the University recruits students from Chinese mainland, Hong Kong, Macao, Taiwan regions and overseas. Undergraduates obtain a graduation certificate and degree certificate from CityUHK (Dongguan), together with a degree certificate from City University of Hong Kong.

CityUHK (Dongguan) offers five undergraduate programmes including Computer Science, Materials Science and Engineering, Energy Science and Engineering, Intelligent Manufacturing Engineering and Data Science, and a suite of taught postgraduate programmes, all at world-leading standards.

Zhang Ziqian, a first-year undergraduate, shared his campus experience. He highlighted the University’s “no-major upon entry” system, English-medium instruction and global exchange opportunities, which enable students to explore academic interests and strengthen international competitiveness.

Professor CHIU Chi Yue, Vice President (Administration), Dr Li Yuan, Associate Vice-President (Teaching and Development), and Professor Li Yi, Head of the Department of Materials Science and Engineering, delivered public lectures on university choice in the AI era, future-ready learning and further education pathways.

Strategically located in Songshan Lake Science City, the University is embedded in an innovation ecosystem alongside major national scientific facilities and leading enterprises. Its Phase II campus, due for completion in 2028, will further enhance research and talent development.

For more information, please visit the University’s website: https://www.cityu-dg.edu.cn/en/home.html

DONGGUAN, China, May 2, 2026 /PRNewswire/ — City University of Hong Kong (Dongguan) held its 2026 Campus Open Day on 1 May, attracting more than 50,000 online and offline visitors, and showcasing its academic strengths, facilities and student-centred learning environment.

Held at main and parallel venues, the Open Day featured university introduction, programme briefings, consultations, student sharing, public lectures and immersive activities.

In his opening address, Professor Lu Chun, Executive President of CityUHK (Dongguan), highlighted the University’s first master’s graduates’ achievements. He noted that the outstanding 2026 graduates demonstrated strong academics, cutting-edge tech mastery and practical experience from top enterprises, with the University aiming to nurture versatile talents for the AI era.

Professor Julie Juan LI, Vice President (Academic) of CityUHK (Dongguan), stated that CityUHK (Dongguan) inherits the world-class academic strengths of CityUHK, which is ranked 63rd globally and 7th in Asia in the 2026 QS World University Rankings, and has been named the “World’s Most International University” by THE for three consecutive years. She underlined the University’s full alignment with CityUHK’s academic standards and resources, sustaining consistent educational excellence through cross-campus collaboration.

In her speech, Ms Yin Rongrong, Director of the Admissions Office, noted that the University recruits students from Chinese mainland, Hong Kong, Macao, Taiwan regions and overseas. Undergraduates obtain a graduation certificate and degree certificate from CityUHK (Dongguan), together with a degree certificate from City University of Hong Kong.

CityUHK (Dongguan) offers five undergraduate programmes including Computer Science, Materials Science and Engineering, Energy Science and Engineering, Intelligent Manufacturing Engineering and Data Science, and a suite of taught postgraduate programmes, all at world-leading standards.

Zhang Ziqian, a first-year undergraduate, shared his campus experience. He highlighted the University’s “no-major upon entry” system, English-medium instruction and global exchange opportunities, which enable students to explore academic interests and strengthen international competitiveness.

Professor CHIU Chi Yue, Vice President (Administration), Dr Li Yuan, Associate Vice-President (Teaching and Development), and Professor Li Yi, Head of the Department of Materials Science and Engineering, delivered public lectures on university choice in the AI era, future-ready learning and further education pathways.

Strategically located in Songshan Lake Science City, the University is embedded in an innovation ecosystem alongside major national scientific facilities and leading enterprises. Its Phase II campus, due for completion in 2028, will further enhance research and talent development.

For more information, please visit the University’s website: https://www.cityu-dg.edu.cn/en/home.html