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
11 days ago
Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed
upvoted
a
paper
about 1 month ago
Budget-Aware Tool-Use Enables Effective Agent Scaling
upvoted
a
paper
about 1 month ago
Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
Organizations
None yet
commented
a
paper
11 months ago