ResearchTechCrunch

Kog is going deeper to squeeze more inference out of GPUs

#ai#inference#startups#gpu#software

English

French startup Kog aims to enhance AI inference speeds using conventional GPUs through software optimization, targeting businesses reliant on AI workflows. The company has demonstrated significant potential with a small model, but acknowledges the need to prove its approach on larger language models to secure further funding.

中文

法国初创公司Kog旨在通过软件优化提升传统GPU的AI推理速度，目标是依赖AI工作流程的企业。该公司已经在一个小模型上展示了显著的潜力，但承认需要在更大语言模型上证明其方法以获得进一步资金支持。