LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
Paper
•
2602.04541
•
Published
•
8
Gang Lin
LG9077
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
12 days ago
LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
Organizations
None yet
upvoted
a
paper
12 days ago