Tsingmicro

Tsingmicro (清微智能) is a Chinese fabless semiconductor company focused on reconfigurable computing architectures, particularly coarse-grained reconfigurable arrays (CGRA), for artificial intelligence inference and edge computing. The company was founded in 2018 in Beijing by a team with backgrounds in academia and the semiconductor industry, and it has positioned itself as an alternative to conventional GPU and FPGA approaches for energy-efficient AI acceleration. Tsingmicro designs chips and IP for applications including smart cameras, robotics, industrial vision, and data-center inference. Its product line includes the TX5 series of reconfigurable AI chips and related software development tools. The company has raised multiple rounds of venture funding from Chinese and international investors, reflecting growing interest in domestic semiconductor capabilities. As a private, venture-backed company, Tsingmicro operates primarily in the Chinese market, serving OEMs and system integrators. It competes with both established chip vendors and other AI chip startups. The company's technology emphasizes flexibility and power efficiency, aiming to address the diverse and rapidly evolving workloads of AI inference at the edge. Tsingmicro has received recognition within China's semiconductor ecosystem and has been included in various industry lists of promising AI chip startups. Its investors include Sequoia China and other venture capital firms. The company continues to develop its chip roadmap and software ecosystem.

Tsingmicro was founded in 2018 in Beijing, China, by a team combining academic research and industry experience in reconfigurable computing. The company emerged during a period of increased investment in China's domestic semiconductor industry, particularly in AI chips. In its early years, Tsingmicro focused on developing its core CGRA technology and securing venture funding. The company raised financing from investors including Sequoia China and Baidu Ventures, among others. It launched its first-generation reconfigurable AI chips, targeting edge applications such as smart surveillance and robotics. By the early 2020s, Tsingmicro had introduced the TX5 series, its flagship line of reconfigurable AI chips, and expanded its software stack to support developers. The company has continued to raise capital and grow its team, positioning itself in the competitive Chinese AI chip market. Tsingmicro has been recognized in industry lists and media coverage as a notable AI chip startup in China. It remains a private company and continues to develop its technology roadmap.

• 2021

  Introduced TX5 series reconfigurable AI chips.

• 2020

  Launched first-generation reconfigurable AI chips for edge applications.

• 2019

  Raised early-stage funding from investors including Sequoia China and Baidu Ventures.

• 2018

  Tsingmicro founded in Beijing, China.

Energy-efficient reconfigurable computing for AI inference at the edge and in the data center.

• TX5 series

  Flagship reconfigurable AI chips for edge and data-center inference.

• CGRA IP

  Coarse-grained reconfigurable array intellectual property for licensing.

• 2026-08-13

  BAAI FlagOS completes Day0 multi-chip adaptation for Alibaba's Qwen3.8-2.4T-A95B[1]智源FlagOS完成阿里Qwen3.8-2.4T-A95B的Day0多芯片适配163.com

  Reported: 2026-08-13

  On August 13, the Beijing Academy of Artificial Intelligence (BAAI) announced that its Zhongzhi FlagOS community completed Day0 multi-chip adaptation for Alibaba's open-source ultra-large MoE model Qwen3.8-2.4T-A95B, with adaptation, precision alignment and deployment validation done on nine AI chips including T-Head, Nvidia, Moore Threads, Huawei Ascend, MetaX, Kunlunxin, Hygon, Qingwei and Suiyuan, offering BF16, FP8 and INT8 precision versions.

1. 1智源FlagOS完成阿里Qwen3.8-2.4T-A95B的Day0多芯片适配163.com