500AI
Back to researchers

Ammar Ahmad Awan

Large-scale transformer inference (DeepSpeed)

Co-authored DeepSpeed Inference: practical inference optimizations for serving large transformer models.

Highlights

SystemsInferenceServing
Focus: Large-scale transformer inference (DeepSpeed)
Why it matters: Co-authored DeepSpeed Inference: practical inference optimizations for serving large transformer models.
Start here
DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scalepaper →DeepSpeed (GitHub)project →

Research Areas

SystemsInferenceServing
Ammar Ahmad Awan - AI Researcher Profile | 500AI