Sail Research
Series ANext-generation sparse transformer inference algorithms and ultra-fast model execution kernels
AI InferenceTotal Raised: $80M👥 11-50 Employees📍 Palo Alto, USA
About Sail Research
Sail Research writes custom CUDA and Triton execution kernels that exploit dynamic activation sparsity in large frontier models, enabling 5x higher throughput per GPU for real-time agentic reasoning chains.
Founders & Leadership
Dr. Jason LinFounder & CEO
Investors & Backers
Funding History
1 roundSimilar Companies in AI Inference
Explore verified active tech startups operating in the AI Inference space.