SambaNova has launched its intelligent AI chip SN40L, which can run models with up to 50 trillion parameters while maintaining model accuracy. The SN40L chip is manufactured by TSMC and provides over 256k sequence length for a single system node, enhancing model quality and inference speed through integrated technology. SambaNova's full-stack large language model (LLM) platform will be powered by the SN40L chip, addressing the challenges enterprises face in deploying generative artificial intelligence. The uniqueness of the SN40L chip lies in its simultaneous processing capabilities.

💻 Chip Specifications: 1.5T memory supports 3 times the parameter scale of GPT-4 📈 Commercial Value: Valued at 36.5 billion RMB with investments from SoftBank and other notable investors 🔨 Product Positioning: Targeted for large enterprises for privatized deployment of large models

SambaNova has launched a new chip capable of running models that are more than twice the size of OpenAI's advanced ChatGPT. The SN40L chip is specifically designed for running large language models in enterprise applications. SambaNova's chips are manufactured by TSMC.