Argonne National Laboratory

AI & ML interests

Disclaimer: This repository is for ANL researchers. The models and files are experimental, ongoing, and not production-ready. They may have inaccuracies, incomplete features, or unstable behavior. Use at your own discretion.

Recent Activity

krishnateja95  authored a paper 16 days ago

MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models

krishnateja95  authored a paper 16 days ago

PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference

krishnateja95  authored a paper 16 days ago

LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference

View all activity

Team members 58