BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

SPARQLe Proposes Sub-Precision Activations For LLM Inference

Sep 12, 2026

SPARQLe proposes sub-precision activation representations to reduce compute and memory costs during quantized language-model inference.

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

More in Open-weight & owned stack