- projects
- thoughts
- blogs
- reviews
- external-services
•
•
•
•
-
MagicDec: Breaking the Latency-Throughput Tradeoff for Long Contexts with Speculative Decoding
MagicDec: Breaking the Latency-Throughput Tradeoff for Long Contexts with Speculative Decoding
-
Reshaping Bonsai
Pruning LLMs for Mathematical Reasoning. Can we prune LLMs while maintaining their mathematical reasoning abilities? How does a novel comprehensive metric affect pruning?
-
Visual Prompt Tuning
Can you transfer prompts? What is the best place to append prompts? Do they increase the adversarial robustness? Find out here :)
