OctoML Announces Faster Machine Learning Model Inferencing on Apple's New M1 Than Apple's Core ML 4 Provides
OctoML Announces Faster Machine Learning Model Inferencing on Apple’s New M1 Than Apple’s Core ML 4 Provides GlobeNewswire 2020-12-16 SEATTLE, Dec. 16, 2020 (GLOBE NEWSWIRE) -- OctoML, the MLOps automation company for superior model performance, portability and productivity, today demonstrated better model performance on Apple’s M1 chip than Apple’s core inferencing engine. OctoML’s results showcased lower model latency than any of Apple’s own developed software, ranging from a 30% improvement against Apple’s latest Core ML 4 infe...
Source: itnewsonline.com