Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters
Paper
•
2406.16758
•
Published
•
19
•
3
Taehyeon Kim
Kthyeon
AI & ML interests
LLM Inference: Parallel, Speculative, Instructive Decoding
Organizations
Kthyeon's activity
commented
a
paper
about 2 months ago