BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

FLRQ Uses Low-Rank Sketching For Faster Quantization

Sep 12, 2026

The FLRQ paper proposes flexible low-rank matrix sketching to reduce the fine-tuning cost of post-training LLM quantization.

Read the original at awesomepapers.ioOpens the publisher's site in a new tab

More in Open-weight & owned stack