SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference
Paper
•
2502.18137
•
Published
•
58
Xiangchendong
Xiang-cd
AI & ML interests
pre-train models
Recent Activity
upvoted
an
article
8 days ago
From DeepSpeed to FSDP and Back Again with Hugging Face Accelerate
upvoted
a
paper
about 1 month ago
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable
Sparse-Linear Attention
liked
a dataset
5 months ago
waltsun/MOAT
Organizations
None yet
authored
a
paper
8 months ago
authored
a
paper
over 1 year ago