UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs
Paper
•
2512.03383
•
Published
•
3
AI & ML interests
Energy-aware Computing, Low Power Design, EDA, Dark Silicon, Efficient Deep Learning
Recent Activity
View all activity
Papers
UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs
Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models
hychiang
authored
a
paper
7 days ago
Add model card for Quamba2
#1 opened about 1 month ago
by
nielsr
Add model card for Quamba2
#1 opened about 1 month ago
by
nielsr
Add model card for Quamba2
#1 opened about 1 month ago
by
nielsr
Add model card for Quamba2
#1 opened about 1 month ago
by
nielsr
hychiang
updated
a
collection
7 months ago
hychiang
updated
a
model
7 months ago
hychiang
published
a
model
7 months ago
hychiang
authored
4
papers
8 months ago
Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models
Paper
•
2503.22879
•
Published
•
9
Quamba: A Post-Training Quantization Recipe for Selective State Space Models
Paper
•
2410.13229
•
Published
•
1
Efficient Low-rank Backpropagation for Vision Transformer Adaptation
Paper
•
2309.15275
•
Published
•
1
MobileTL: On-device Transfer Learning with Inverted Residual Blocks
Paper
•
2212.03246
•
Published
•
1
hychiang
updated
a
collection
8 months ago
hychiang
updated
a
model
8 months ago
hychiang
updated
a
collection
8 months ago