Search Results
Mar 16, 2026, 16:35 ET Supermicro Reveals DCBBS® with New NVIDIA Vera Rubin NVL72, HGX Rubin NVL8, and Vera CPU Systems, Designed to Accelerate Customer Time-to-Market
SuperNIC, NVIDIA BlueField-4 DPU, and NVIDIA Spectrum-X Ethernet — to deliver up to 3.6 Exaflops of inference, 75TB of fast memory, and 1.6 PB/s of HBM4 bandwidth, targeting up to 10x the throughput per watt and one-tenth the token cost compared to NVIDIA Blackwell.NVIDIA HGX Rubin
More news about: Super Micro Computer, Inc.
Mar 16, 2026, 16:35 ET Supermicro Reveals DCBBS® with New NVIDIA Vera Rubin NVL72, HGX Rubin NVL8, and Vera CPU Systems, Designed to Accelerate Customer Time-to-Market
SuperNIC, NVIDIA BlueField-4 DPU, and NVIDIA Spectrum-X Ethernet — to deliver up to 3.6 Exaflops of inference, 75TB of fast memory, and 1.6 PB/s of HBM4 bandwidth, targeting up to 10x the throughput per watt and one-tenth the token cost compared to NVIDIA Blackwell.NVIDIA HGX Rubin NVL8 SystemThe
More news about: Super Micro Computer, Inc.
Mar 16, 2026, 16:30 ET MSI Launches XpertStation WS300 on NVIDIA DGX Station Architecture
XpertStation WS300 integrates up to 748GB of large coherent memory, combining high-bandwidth HBM3e GPU memory and LPDDR5X CPU memory into a unified domain to enable efficient CPU-GPU data sharing for large-scale model training and fine-tuning.With
More news about: MSI
Mar 16, 2026, 16:30 ET PEGATRON Unveils Next Generation AI Platforms Powered by NVIDIA Vera Rubin NVL72 and NVIDIA HGX Rubin NVL8 at GTC 2026
Spectrum-X Ethernet networking, the solution delivers 3.6 EFLOPS inference performance, 260 TB/s bandwidth, and 20.7 TB HBM4 memory. Compared with NVIDIA
More news about: PEGATRON CORPORATION
Mar 16, 2026, 16:30 ET WEKA Maximizes Token Output With Lower Cost Per Token on NVIDIA BlueField-4 STX
AI economics are decided at the memory infrastructure layer. Every large-scale inference fleet hits the memory wall: limited high-bandwidth memory (HBM) on the GPU is rapidly exhausted, key-value (KV) cache is evicted, context is lost, and the system is forced to repeat work it already completed. This
More news about: WEKA
Mar 16, 2026, 16:30 ET WEKA Maximizes Token Output With Lower Cost Per Token on NVIDIA BlueField-4 STX
AI economics are decided at the memory infrastructure layer. Every large-scale inference fleet hits the memory wall: limited high-bandwidth memory (HBM) on the GPU is rapidly exhausted, key-value (KV) cache is evicted, context is lost, and the system is forced to repeat work it already completed. This
More news about: WEKA
Mar 16, 2026, 16:30 ET WEKA maximiert die Token -Produktion bei geringeren Kosten pro Token auf NVIDIA BlueField-4 STX
entscheidet sich auf der Ebene der Speicherinfrastruktur. Jede groß angelegte Inferenzflotte stößt an die Speichergrenze: Der begrenzte High-Bandwidth-Memory (HBM) auf der GPU ist schnell erschöpft, der Key-Value (KV)-Cache wird geleert, der Kontext geht verloren und das System ist gezwungen, bereits abgeschlossene
More news about: WEKA
Mar 13, 2026, 10:00 ET Is your AI infra ready for the era of Agentic AI? Agents mean new headaches for AI Infra teams
KV-cache requirements driven by larger context windows and persistent AI sessionsEfficient offloading of context memory from GPU HBM and system DRAMHigh-performance shared storage capable of serving context data to large GPU clustersScalable infrastructure
More news about: ScaleFlux, Inc.
Mar 12, 2026, 08:00 ET AI Infrastructure Expansion Drives Data Center IT Component Market Growth, According to Dell'Oro Group
NVIDIA's performance reflected the strong ramp of the Blackwell platform, which includes GPUs, CPUs, and NICs. SK Hynix and Samsung benefited from surging HBM demand and rising DRAM and SSD prices.High-end accelerators will remain the largest contributor to revenue growth in 2026, supported by the
More news about: Dell'Oro Group
Mar 10, 2026, 08:00 ET Phononic's Expanded Data Center Cooling Portfolio Delivers 3X ROI for AI Data Centers, Ushering in a New Era of AI Data Center Performance
Phononic's Broadened Suite of Solid State Cooling Technologies for AI Datacenters:Sampling Next Gen HBM4 Aligned GPU HBM Cooling Solutions – A solution that enables 75% higher heat dissipation which allows for higher sustained GPU performance, reduces thermal-induced
More news about: Phononic
Mar 09, 2026, 06:47 ET 科倫博泰與和鉑醫藥宣佈SKB575/HBM7575治療特應性皮炎的新藥臨床試驗申請獲NMPA批准
關於SKB575/HBM7575SKB575/HBM7575是一款靶向胸腺基質淋巴細胞生成素（TSLP）及一個未公開靶點的長效雙特異性抗體，具有雙重作用機制：一方面通過阻斷TSLP與其受體的相互作用，可抑制TSLP介導的信號通路以及Th2免疫細胞的啟動；另一方面，其針對另一未公開靶點的結合與阻斷可產生協同效應，克服TSLP單靶點抗體的耐藥問題。SKB575/HBM7575經過工程化設計，具有延長的半衰期以及良好的可開發性，可實現皮下給藥。基於臨床前半衰期推測，人體半衰期預期可支援3個月以上的給藥間隔，具備同類最佳的潛力。根據公
More news about: 科倫博泰
Mar 09, 2026, 06:47 ET Kelun-Biotech and Harbour BioMed Announce NMPA Approval of IND Application for SKB575/HBM7575 for the Treatment of Atopic Dermatitis
profile, SKB575/HBM7575 holds the potential to deliver durable and stable disease control while improving patient treatment experience through reduced dosing frequency."Dr. Jingsong Wang, Founder, Chairman, and CEO of Harbour BioMed, commented: "The NMPA's IND approval for HBM7575/SKB575 marks
More news about: Kelun-Biotech
Mar 09, 2026, 04:32 ET Harbour BioMed and Kelun-Biotech Announce NMPA Approval of IND Application for HBM7575/SKB575 for the Treatment of Atopic Dermatitis
commented: "The NMPA's IND approval for HBM7575/SKB575 marks an important step forward in addressing the significant unmet needs in autoimmune diseases such as atopic dermatitis. By targeting TSLP, a key upstream driver of type 2 inflammation, and an undisclosed target, HBM7575/SKB575 has the potential to be
More news about: Harbour BioMed
Mar 05, 2026, 12:05 ET CIQ Introduces the CIQ Linux Kernel, Built to Unlock the Full Performance of Modern AI Hardware in Enterprise Production
CLK. When a CVE is fixed upstream, it is fixed in CLK.Emerging technology support: Features such as io_uring, eBPF, memory tiering (CXL/HBM) and confidential computing extensions (TDX, SEV-SNP) reach CLK users in production-ready form as they are stabilized upstream.Rocky Linux
More news about: CIQ
Mar 05, 2026, 09:00 ET Rayence Expands High-Speed CMOS X-ray Detector "Flash Series" for Semiconductor AXI and 3D X-ray CT Inspection in AI and HBM Manufacturing
demand for AI- and HBM- focused inspection continues to rise and translates into global equipment orders, its industrial detector revenue is expected to remain stable in the first quarter of this year."As AI infrastructure continues to expand and the structural complexity of HBM and AI chips deepens,
More news about: Rayence
Mar 05, 2026, 08:32 ET Supply Chain Control Enables Apple to Launch Lower-Priced Notebooks Amid Industry Downturn to Fill Pricing Gap, Says TrendForce
TrendForceTrendForce is a global leader in technology industry analysis and consulting services. With deep expertise spanning foundry, DRAM, HBM, NAND Flash, AI servers, robotics, near-eye displays, display panels, LEDs, MLCC, and green energy, it also offers in-depth research into key market
More news about: TrendForce
Mar 04, 2026, 15:21 ET Akash Systems anuncia os primeiros servidores de IA do mundo resfriados por diamante com GPUs AMD Instinct™ MI350X e MiTAC Computing
sistemas de satélites ativos.Com uma redução inovadora de temperatura de até 10 °C (18 °F) tanto na GPU quanto na memória de alta largura de banda (HBM), os operadores obtêm significativamente mais processamento dos mesmos sistemas de energia – melhorando a eficiência energética e de capital, a eficácia
More news about: MiTAC Computing Technology Corp.
Mar 04, 2026, 15:18 ET Akash Systems anuncia los primeros servidores de IA refrigerados por diamante del mundo con GPU AMD Instinct™ MI350X y MiTAC Computing
activos.Con una reducción revolucionaria de la temperatura de hasta 10 °C (18 °F) tanto en la GPU como en la memoria de alto ancho de banda (HBM, por sus siglas en inglés), los operadores obtienen una potencia de cálculo muy superior con los mismos sistemas de alimentación, lo que mejora la eficiencia
More news about: MiTAC Computing Technology Corp.
Mar 04, 2026, 15:12 ET Spoločnosť Akash Systems predstavuje prvé diamantom chladené servery s umelou inteligenciou na svete, grafickými procesormi AMD Instinct™ MI350X a výpočtovou technikou MiTAC
aktívnych satelitných systémoch.Vďaka prelomovému zníženiu teploty až o 10 °C (18 °F) na grafickej karte aj na pamäti s vysokou šírkou pásma (HBM) získavajú operátori výrazne viac výpočtového výkonu z rovnakých napájacích systémov – čím sa zlepšuje kapitálová a energetická účinnosť, efektívnosť
More news about: MiTAC Computing Technology Corp.
Mar 04, 2026, 15:09 ET Akash Systems анонсирует первые в мире ИИ-серверы с алмазным охлаждением на базе графических процессоров AMD Instinct™ MI350X производства MiTAC Computing
спутниковых системах.Благодаря прорывному снижению температуры до 10 °C (18 °F) как на графическом процессоре, так и на высокоскоростной памяти (HBM) операторы получают значительно больше вычислений при одних и тех же энергосистемах – повышение капитало- и энергоэффективности, эффективности использования
More news about: MiTAC Computing Technology Corp.
Mar 04, 2026, 15:01 ET Akash Systems kündigt die weltweit ersten KI-Server mit Diamond Cooling® sowie AMD Instinct™ MI350X GPUs und MiTAC Computing an
Einsatz ist.Mit einer bahnbrechenden Temperatursenkung von bis zu 10 °C (18 °F) sowohl bei der GPU als auch beim Speicher mit hoher Bandbreite (HBM) erhalten Betreiber deutlich mehr Rechenleistung aus denselben Stromversorgungssystemen. Dadurch verbessern sich Kapital- sowie Energieeffizienz, Stromverbrauchseffizienz
More news about: MiTAC Computing Technology Corp.
Mar 04, 2026, 14:56 ET Akash Systems annonce les premiers serveurs d'IA à refroidissement par diamant au monde avec les processeurs graphiques AMD Instinct™ MI350X et MiTAC Computing
actifs.Grâce à une réduction significative de la température pouvant atteindre 10 °C (18 °F) du processeur graphique et de la mémoire à large bande passante (HBM), les opérateurs bénéficient d'une puissance de calcul nettement supérieure à partir des mêmes systèmes d'alimentation, améliorant ainsi l'efficacité
More news about: MiTAC Computing Technology Corp.
Mar 04, 2026, 12:31 ET Akash Systems công bố máy chủ AI làm mát bằng kim cương đầu tiên trên thế giới sử dụng GPU AMD Instinct™ MI350X và hợp tác cùng MiTAC Computing
động trên các hệ thống vệ tinh đang hoạt động.Với khả năng giảm nhiệt độ đột phá lên tới 10°C (18°F) trên cả GPU và Bộ nhớ Băng thông Cao (HBM), các nhà vận hành đạt được năng lực tính toán lớn hơn đáng kể trên cùng một hệ thống điện năng – cải thiện hiệu quả vốn đầu tư và năng lượng, Hiệu
More news about: MiTAC Computing Technology Corp.
Mar 04, 2026, 09:58 ET Akash Systems Luncurkan Server AI Pertama di Dunia dengan Teknologi Pendingin Berbahan Berlian yang Didukung GPU AMD Instinct™ MI350X dan MiTAC Computing
angkasa, dan saat ini beroperasi pada sistem satelit aktif.Dengan penurunan suhu hingga 10°C (18°F) pada GPU dan High Bandwidth Memory (HBM), operator pusat data memperoleh kapasitas komputasi yang jauh lebih besar dari sistem daya yang sama. Hal tersebut meningkatkan efisiensi energi dan
More news about: MiTAC Computing Technology Corp.
Mar 04, 2026, 03:00 ET TCL CSOT Pushes Mobile Displays Beyond Limits with Super Pixel at MWC 2026
efficiency. With FIAA fine-pitch technology, bezels are reduced to 0.75 mm on the sides and 0.79 mm at the bottom, while 2000 nits High Brightness Mode (HBM) and a 3,200-nits peak Average Picture Level (APL) ensure clarity even in strong ambient light, delivering an immersive experience for gamers and video
More news about: TCL CSOT