Rui Pan

ruipeterpan's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 2 papers 9 months ago

SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning

Paper • 2504.07891 • Published Apr 10 • 5

Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving

Paper • 2312.05385 • Published Dec 8, 2023

authored 2 papers 12 months ago

RAGServe: Fast Quality-Aware RAG Systems with Configuration Adaptation

Paper • 2412.10543 • Published Dec 13, 2024 • 1

Marconi: Prefix Caching for the Era of Hybrid LLMs

Paper • 2411.19379 • Published Nov 28, 2024 • 1