MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models
Paper
•
2508.17467
•
Published
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.
krishnateja95
authored
4
papers
3 months ago
PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
Paper
•
2509.04377
•
Published
LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference
Paper
•
2509.02753
•
Published
ImageNet-Think-250K: A Large-Scale Synthetic Dataset for Multimodal Reasoning for Vision Language Models
Paper
•
2510.01582
•
Published
memani
authored
5
papers
3 months ago
AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons
Paper
•
2503.05731
•
Published
•
3
LM4HPC: Towards Effective Language Model Application in High-Performance Computing
Paper
•
2306.14979
•
Published
AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions
Paper
•
2509.13523
•
Published
•
7
MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models
Paper
•
2508.17467
•
Published
PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
Paper
•
2509.04377
•
Published
Sand33p
authored
5
papers
3 months ago
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Paper
•
2301.07799
•
Published
AstroMLab 1: Who Wins Astronomy Jeopardy!?
Paper
•
2407.11194
•
Published
Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry
Paper
•
2411.15221
•
Published
•
30
EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistants
Paper
•
2502.20309
•
Published
Scaling transformer neural networks for skillful and reliable medium-range weather forecasting
Paper
•
2312.03876
•
Published
samforeman
authored
a
paper
3 months ago
Sand33p
authored
a
paper
3 months ago
Zilinghan
authored
4
papers
5 months ago
FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices using a Computing Power Aware Scheduler
Paper
•
2309.14675
•
Published
EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistants
Paper
•
2502.20309
•
Published
Pathology Image Compression with Pre-trained Autoencoders
Paper
•
2503.11591
•
Published
•
4
PixCell: A generative foundation model for digital histopathology images
Paper
•
2506.05127
•
Published
•
3