LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
Paper
•
2502.14866
•
Published
•
12
Jiaming Tang
Dudep
AI & ML interests
NLP, LLM, Causal Inference
Recent Activity
authored
a paper
6 days ago
LServe: Efficient Long-sequence LLM Serving with Unified Sparse
Attention
updated
a model
3 months ago
Dudep/opt-critic
updated
a model
3 months ago
Dudep/opt-critic
Organizations
None yet
Dudep's activity
authored
a
paper
6 days ago
updated
2
models
3 months ago