Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding
Paper • 2502.05609 • Published • 18 •
3
Sukmin Cho
zomss
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? upvoted a paper 2 months ago
Understanding Reasoning in LLMs through Strategic Information Allocation under UncertaintyOrganizations
None yet
commented a
paper over 1 year ago