TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference Acceleration
Paper • 2608.17336 • Published • 5
Hanzhi Zhang
HanzhiZhang
·
AI & ML interests
Responsible AI, Efficient LLMs, Hardware-aware ML, Small Language Models
Recent Activity
updated a dataset 4 days ago
HanzhiZhang/Poly-FEVER upvoted a paper 10 days ago
TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference Acceleration submitted a paper 10 days ago
TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference AccelerationOrganizations
None yet