FedMef: Towards Memory-efficient Federated Dynamic Pruning
Paper • 2403.14737 • Published
Hong Huang
HongHuang
AI & ML interests
Efficient & Reliable AI
Recent Activity
authored a paper about 11 hours ago
FedMef: Towards Memory-efficient Federated Dynamic Pruning authored a paper about 11 hours ago
Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification authored a paper about 11 hours ago
AngelSlim: A more accessible, comprehensive, and efficient toolkit for large model compressionOrganizations
authored 4
papers about 11 hours ago
Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification
Paper • 2601.07892 • Published • 4
AngelSlim: A more accessible, comprehensive, and efficient toolkit for large model compression
Paper • 2602.21233 • Published • 3
Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?
Paper • 2603.00166 • Published
Update STQ1_0 kernel
#1 opened 2 days ago
by HongHuang
Update README.md
#2 opened 2 days ago
by HongHuang
it can not be loaded by the newest version llama.cpp..... which version do you use when developing ?
👍 1
3
#2 opened 11 days ago
by 
JamesYdAtJ3
Mobile app
1
#3 opened 2 days ago
by 
NickupAI
how to deploy AngelSlim/Hy-MT1.5-1.8B-1.25bit
2
#1 opened 12 days ago
by 
Aelous
Is the STQ runtime kernel for the 1.25-bit model open-sourced?
3
#3 opened 11 days ago
by 
baicai1145
Problem: No model loads in LMStudio
➕ 1
1
#6 opened 3 days ago
by 
Alex3233
updated 2
models 2 days ago
Can you please make the demo app better?
2
#1 opened 2 days ago
by 
abskvrm
updated a
collection 3 days ago
请教大佬们一个问题？
3
#1 opened 11 days ago
by 
DoraemonTom
Problem : android app ui only in Chinese
1
#5 opened 9 days ago
by 
maroo87
liked a
model 12 days ago
updated 2
models 12 days ago