Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts
Paper • 2610.02241 • Published • 4
Kwanhee Lee
kwanhee
AI & ML interests
Model compression, optimization
Recent Activity
new activity 9 days ago
ISTA-DASLab/Kimi-K2.5-P48NVFP4-MoESQ:diamond degradation upvoted a paper 12 days ago
Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts upvoted a collection 12 days ago
MoESQOrganizations
diamond degradation
2
#1 opened 18 days ago
by 
MB66166
upvoted a paper 12 days ago
upvoted a collection 12 days ago
authored 2
papers 14 days ago
updated a
model 14 days ago
updated a
collection 14 days ago
published a
model 14 days ago
updated 4
models 14 days ago
ISTA-DASLab/Qwen3.8-Flash-Next-P48NVFP4-MoESQ
Text Generation • 135B • Updated • 1.05k • 10
ISTA-DASLab/Qwen3.5-397B-A17B-P48NVFP4-MoESQ
Image-Text-to-Text • 258B • Updated • 73
ISTA-DASLab/Qwen3-30B-A3B-P48NVFP4-MoESQ
Text Generation • 20B • Updated • 749 • 3
ISTA-DASLab/Kimi-K2.5-P48NVFP4-MoESQ
Text Generation • 646B • Updated • 548 • 1
updated a
collection 14 days ago
updated a
collection 16 days ago
published a
model 16 days ago
updated a
collection 20 days ago
published a
model 20 days ago
updated a
collection 20 days ago
published a
model 20 days ago
updated a
collection 20 days ago