TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation
Paper
•
2602.04929
•
Published
•
1
Junhan
SShock92
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
4 days ago
TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation
authored
a paper
over 1 year ago
Towards Next-Level Post-Training Quantization of Hyper-Scale
Transformers
authored
a paper
over 1 year ago
Attention-aware Post-training Quantization without Backpropagation
Organizations
None yet