SiMa.ai’s Palette 3.0 runs many AI models on one chip and lifts throughput up to 3.5 times

Posted

Physical artificial intelligence chip startup SiMa Technologies Inc. today released Palette 3.0, a new version of its Palette software suite intended to allow many AI models to run concurrently on one chip. According to the company, the release, which builds on the Palette Neat agentic development environment launched in June, can raise model throughput by […]

The post SiMa.ai’s Palette 3.0 runs many AI models on one chip and lifts throughput up to 3.5 times appeared first on SiliconANGLE.



Continue reading at SiliconANGLE »

Infra, NEWS, The-Latest, AI, Amplify Partners, artificial intelligence, autonomous machines, Developer Center, DFlash, Docker, drones, EAGLE3, Emerson Electric, Fidelity Management & Research, Gemma 4 MTP, generative AI, GitHub, gpt-oss-20b, Krishna Rangasayee, large language models, Mixture of Experts, Modalix, Modalix MLSoC, model registry, Open Source, OpenAI, Palette, Palette 3.0, Palette Neat, physical AI, Robert Bosch, robots, SiMa Technologies, Sima.ai, speculative decoding, Synopsys, vision language models