LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
Paper
•
2502.14866
•
Published
•
8
Guangxuan Xiao
Guangxuan-Xiao
AI & ML interests
Efficient Machine Learning
Recent Activity
authored
a paper
2 days ago
LServe: Efficient Long-sequence LLM Serving with Unified Sparse
Attention
authored
a paper
4 months ago
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and
Streaming Heads
upvoted
a
paper
4 months ago
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and
Streaming Heads
Organizations
Guangxuan-Xiao's activity
authored
a
paper
2 days ago
authored
a
paper
4 months ago
upvoted
a
paper
4 months ago
commented
a
paper
4 months ago
updated
2
models
5 months ago
authored
5
papers
7 months ago
Offsite-Tuning: Transfer Learning without Full Model
Paper
•
2302.04870
•
Published
Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
Paper
•
2406.10774
•
Published
•
2
QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving
Paper
•
2405.04532
•
Published
Retrieval Head Mechanistically Explains Long-Context Factuality
Paper
•
2404.15574
•
Published
•
2
InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory
Paper
•
2402.04617
•
Published
•
4
updated
2
models
7 months ago
updated
a
dataset
7 months ago
updated
a
model
12 months ago
liked
a
model
12 months ago
authored
a
paper
about 1 year ago
updated
a
model
about 1 year ago
authored
2
papers
over 1 year ago