arxiv:2411.19146
Ran Rubin
ranrubin
AI & ML interests
None yet
Recent Activity
liked a dataset 2 days ago
nvidia/SPEED-Bench upvoted an article 2 days ago
**Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding** authored a paper over 1 year ago
Puzzle: Distillation-Based NAS for Inference-Optimized LLMsOrganizations
None yet