Sangfor unveils YuanNao SD200 Ultra AI server at AICC2026
technology1 h ago
coda.news AI summary
- Inspur Information announced the YuanNao SD200 Ultra ultra-node AI server at AICC2026.
- The SD200 Ultra runs the Kimi K3 model with 28 trillion parameters on a single machine.
- Token generation latency for the SD200 Ultra is 5.85 milliseconds.
- Inspur Information also unveiled the YuanNao HC2000 multi-sourced compute unit.
36KrRead original ↗