Inference Acceleration

5 posts · 2 sources

Together AIBlog19 Feb

Consistency diffusion language models: Up to 14x faster inference without sacrificing quality

Together AIBlog3 Dec

Introducing AutoJudge: Streamlined inference acceleration via automated dataset curation

CerebrasBlog11 Mar

Innovations in Virtual Drug Screening

CerebrasBlog4 Mar

Introducing Sparse Llama: 70% Smaller, 3x Faster, Full Accuracy

CerebrasBlog3 Mar

Harnessing the Power of Sparsity for Large GPT AI Models