zunhaisu

zunhai

·

AI & ML interests

None yet

Recent Activity

authored a paper about 17 hours ago

QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching

upvoted a paper about 20 hours ago

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining

upvoted a paper about 20 hours ago

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression

View all activity

Organizations

Papers 13

arxiv:2609.36760

arxiv:2608.12149

arxiv:2608.08627

arxiv:2605.19660

models 0

None public yet

datasets 0

None public yet