Seonglae ChoNPU Frameworks
System on Chip - npu
Intel, Arm and Nvidia propose new standard to make AI processing more efficient
Intel, Arm and Nvidia have proposed a standard that they say can reduce the amount of memory and processing power required for AI workloads.
https://techcrunch.com/2022/09/14/intel-amd-and-nvidia-propose-new-standard-to-make-ai-processing-more-efficient/
Furiosa
Meet the ‘Mad Max’-Loving CEO Challenging Nvidia With a Renegade Chip
June Paik spurned a takeover offer from Meta Platforms last year. Now his company has an AI chip entering mass production.
https://www.wsj.com/tech/ai/furiosa-chip-nvidia-challenge-june-paik-5d3dc304
Robellions
Rebellions
Drive AI Innovation. Simple. Fast. At Scale.
https://rebellions.ai/
RBLN SDK USER GUIDE -
The RBLN SDK is an end-to-end software stack for running AI models on Rebellions NPUs — from the driver, compiler, and runtime up to profiling, serving, and cloud-native deployment on Kubernetes.
https://docs.rbln.ai/latest/