100 Papers
05: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness(
Flash Attention
)
About
00 Preparation for following
100 Papers
01: Attention is All You Need(
Transformer
)
02: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale(
ViT
)
03: Swin Transformer: Hierarchical Vision Transformer using Shifted Windows(
Swin Transformer
)
04: Learning Transferable Visual Models From Natural Language Supervision(
CLIP
)
05: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness(
Flash Attention
)
100 Papers
05: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness(
Flash Attention
)
05: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness(
Flash Attention
)
Author
Yuyang Zhang
This post introduce Flash Attention.
04: Learning Transferable Visual Models From Natural Language Supervision(
CLIP
)