Latest

• CacheGen: KV Cache Compression and Streaming for Fast Language Model Serving
• Eloquent: A More Robust Transmission Scheme for LLM Token Streaming
• CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
• Automatic and Efficient Customization of Neural Networks for ML Applications
• GRACE: Loss-Resilient Real-Time Video through Neural Codecs
• Earth+: on-board satellite imagery compression leveraging historical earth observations
• OneAdapt: Fast Adaptation for Deep Learning Applications via Backpropagation
• Run-Time Prevention of Software Integration Failures of Machine Learning APIs
• AccMPEG: Optimizing Video Encoding for Video Analytics