Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters
Paper
•
2406.16758
•
Published
•
20
Taehyeon Kim
Kthyeon
AI & ML interests
LLM Inference: Parallel, Speculative, Instructive Decoding
Organizations
authored
5
papers
over 1 year ago
Block Transformer: Global-to-Local Language Modeling for Fast Inference
Paper
•
2406.02657
•
Published
•
41
Towards Fast Inference: Exploring and Improving Blockwise Parallel Drafts
Paper
•
2404.09221
•
Published
•
1
Distort, Distract, Decode: Instruction-Tuned Model Can Refine its Response from Noisy Instructions
Paper
•
2311.00233
•
Published
•
4
Navigating Data Heterogeneity in Federated Learning: A Semi-Supervised Approach for Object Detection
Paper
•
2310.17097
•
Published
•
3