LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
Paper
•
2502.14866
•
Published
•
13
Yujun Lin
synxlin
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
30 days ago
VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference
upvoted
a
paper
3 months ago
Fast-dLLM v2: Efficient Block-Diffusion LLM
upvoted
a
paper
3 months ago
DC-VideoGen: Efficient Video Generation with Deep Compression Video
Autoencoder
Organizations
authored
a
paper
10 months ago