arxiv:2502.05003
Alistarh
d-alistarh
AI & ML interests
NLP
Recent Activity
upvoted a collection 22 days ago
Panza upvoted a paper about 1 month ago
WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms upvoted a paper 3 months ago
GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding