method · first seen 5 Oct 2026
tile-based quantization
Quantizing weights in GPU-aligned two-dimensional blocks so precision allocation matches hardware execution units.
Mentions per week
PapersCodeDiscussion
Earliest sources
- AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM GenerationPapers · 5 Oct 2026 · Hanzhi Zhang, Qiao Zhang, Qinglei Cao, Heng Fan, Yan Huang, Kewei Sha, Yunhe Fen…
Latest sources
- AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM GenerationPapers · 5 Oct 2026 · Hanzhi Zhang, Qiao Zhang, Qinglei Cao, Heng Fan, Yan Huang, Kewei Sha, Yunhe Fen…