
全球首款!进迭时空 RISC-V AI CPU K3 成功适配 OpenHarmony 6.1
Quick Answer
The K3 RISC-V AI CPU, developed by Jindie Shikong, successfully runs OpenHarmony 6.1, marking the first RISC-V chip to support this version.
Quick Take
The K3 RISC-V AI CPU, developed by Jindie Shikong, successfully runs OpenHarmony 6.1, marking the first RISC-V chip to support this version. This collaboration enhances compatibility for AI applications in smart terminals and IoT, providing a robust solution with 130 KDMIPS and 60 TOPS performance.
Key Points
- K3 chip achieves full-stack autonomy, enhancing AI computing capabilities.
- OpenHarmony 6.1 offers three years of official maintenance support.
- K3 supports large models with 300-800 billion parameters efficiently.
- The collaboration aims to foster a thriving open-source Harmony ecosystem.
- K3 is suitable for AI computers, smart robots, and intelligent servers.
Article Excerpt
From source RSS / original summary近日,进迭时空与中国科学院软件研究所携手取得重要技术突破——RISC-V AI CPU 芯片 K3 成功运行 OpenHarmony 6. 1 系统,成为全球首款支持 OpenHarmony 6. 1 版本的 RISC-V 架构芯片,标志着 RISC-V 芯片与开源鸿蒙操作系统的适配,正式步入“芯片+系统”全自主、双开源的全新阶段。 在此次适配过程中,双方发挥各自技术优势、深度合作:▲软件所提供 OpenHarmony 系统层技术支持,完成 RISC-V 架构支持与核心组件移植▲进迭时空负责 K3 芯片的底层硬件适配、驱动开发与性能调优这一组合真正实现从芯片到系统的全栈自主,为智能终端、物联网等领域提供了更加安全可控的解决方案OpenHarmony 6.
1是 OpenHarmony 社区推出的 LTS(Long-Term Support)长周期维护版本,相比之前版本,其优势在于:▲长达3年的官方维护支持,保障产品长期稳定迭代,更适合企业生产环境部署▲应用开发能力显著增强,支持更精细化的应用控制,动效体验更流畅▲系统级功能与多媒体体验升级,系统感知、证书管理、音频控制、图形处理能力全面增强作为这一组合的硬件底座,K3 是进迭时空的新一代 RISC-V AI CPU 旗舰处理器,具备 130 KDMIPS 通用算力 与 60 TOPS AI 算力,可高效运行 300-800 亿参数大模型,并支持完整虚拟化及 PCIe、USB 等主流外设接口。 K3 对 OpenHarmony 6. 1 的完美适配,使其可广泛应用于端侧 AI 计算机、智能机器人、智算服务器等智能终端场景中。 这不仅再次验证了 K3 芯片的强大兼容性和成熟度,也为广大 OpenHarmony 开发者提供了全新的高性能硬件选择。 未来,进迭时空将继续与软件所及 OpenHarmony 社区紧密合作,持续优化芯片对其系统的支持,推出更多适配 OpenHarmony 的芯片产品,助力开源鸿蒙生态繁荣发展。
全栈自主,未来已来。 进迭时空将与你一起,共同打造开放共赢的智能终端新生态。
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from 雷峰网芯片
See more →Token账单迷雾:当每百万Token多少钱变成「比价陷阱」
The rise of Token billing in AI has transformed costs into operational expenses, with prices varying significantly due to factors like model efficiency, energy costs, and contract terms. As companies shift from GPU hours to Token-based billing, understanding the hidden complexities behind Token pricing becomes crucial for effective budgeting.

