Ribar, Luka
- SparQ Attention: Bandwidth-Efficient LLM Inference
2023/12/08 by Luka Ribar, Ivan Chelombiev, Ribar, Luka +9 · 23 citations
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Natural Language Processing Techniques #Topic Modeling
- Approximate Top-k for Increased Parallelism
2024/12/05 by Oscar Key, Luka Ribar, Key, Oscar +6 · 2 citations
Computer Science · #Complexity and Algorithms in Graphs #Advanced Graph Theory Research #Coding theory and cryptography