Training Transformers with 4-bit Integers
Paper
•
2306.11987
•
Published
•
22
Haocheng Xi
Xihc20
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable
Sparse-Linear Attention
Organizations
authored
a
paper
over 2 years ago