Iluvatar CoreX Tiangai 300 tops Nvidia H200 in select AI inference tests, with long-context and MoE gains
DIGITIMESen

Chinese AI chipmaker Iluvatar CoreX has released benchmarks showing its next-generation Tiangai 300 general-purpose GPU outperforming Nvidia's H200 in selected large language model (LLM) inference, long-context processing and multimodal generation workloads.
This is a short summary published by AI Global Wire. The full article is owned and hosted by DIGITIMES — open it there to read it in full.
Read the full story at DIGITIMESRelated AI news
- Linus Torvalds 釋出最新 Linux 核心 RC 版,肯定 AI 參與開發模式漸趨「健康」TechNews (TW) · November 2, 2026
- Suomalaisyritys yrittää ratkoa rakennusalan kipukohtaa tekoälyllä – Sai kasvuun miljoonatuenTivi · November 2, 2026
- Le philosophe Jean-Gabriel Ganascia livre un essai éclairant sur les mythes que suscite l’intelligence artificielleLe Monde Pixels · November 2, 2026
- 은행권, 지원 끝난 DB 교체 나선다…보안·장애 위험 선제 대응ETNews (KR) · November 2, 2026
- CoWoS 供應瓶頸浮現,Intel EMIB-T 開闢另一條封裝路線TechNews (TW) · November 2, 2026
- 新型 Windows 惡意軟體曝光,利用 Claude 評估資料價值後自動刪除TechNews (TW) · November 2, 2026