Updates
Introducing ‘Tally’: A Novel Method of Efficient GPU Sharing for AI Workloads
Tally allows multiple AI tasks to share the same GPU, allowing for superior infrastructure efficiency.
Leading Compiler Engineer and Researcher Tatiana Shpeisman Joins CentML as Director of Engineering
Tatiana brings more than two decades of experience in groundbreaking compiler development to the CentML team.
CServe Now on Snowflake: Deploy Secure, Optimized LLMs For Less
This groundbreaking solution allows you to self-host LLMs with 81% lower compute costs, enhanced security, and flexible model support.
A Fine-Tuning Breakthrough: CentML’s New Sylva Method Revolutionizes LLM Adaptation
Learn about CentML’s next-gen fine-tuning, which will take your LLM performance to new heights.
