arxiv:2404.00456
Bo Li
bobboli
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 16 hours ago
LServe: Efficient Long-sequence LLM Serving with Unified Sparse
Attention
upvoted
a
paper
about 16 hours ago
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model
Post-training
authored
a paper
11 months ago
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
Organizations
Papers
1
models
None public yet
datasets
None public yet