Sangfor unveils YuanNao SD200 Ultra AI server at AICC2026
According to 36Kr, at the 2026 AI Computing Conference (AICC2026), Inspur Information announced the YuanNao SD200 Ultra ultra-node AI server, based on domestic AI chips, capable of running the Kimi K3 model with 28 trillion parameters and a token generation latency of 5.85 milliseconds. The company also unveiled the YuanNao HC2000 multi-sourced compute unit.
Key facts
- 01Inspur Information announced the YuanNao SD200 Ultra ultra-node AI server at AICC2026.
- 02The SD200 Ultra runs the Kimi K3 model with 28 trillion parameters on a single machine.
- 03Token generation latency for the SD200 Ultra is 5.85 milliseconds.
- 04Inspur Information also unveiled the YuanNao HC2000 multi-sourced compute unit.
AI-generated from the sources below. Always check the originals.
How each country tells it
So far our sources show coverage from one country. Perspectives appear once we find reports from a second country.
Sources
Summaries are AI-generated from the linked sources and may contain errors; always check the originals. We summarise and link; we never republish articles. Photos come from openly licensed libraries, official publicity material and brand logos, credited to their sources. If you own an image and want it credited differently or removed, email info@coda.news and we will act promptly.