← All talks

ICERM — Fusing Theory and Practice of Graph Algorithms Lightning talk

QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead

Providence, RI, USA

Workshop program · AAAI conference paper · Full QJL presentation

Open original PDF Download PDF
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead — slide 1 of 6
Slide 1 of 6 · Select the slide to view it at full size.
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead — slide 2 of 6
Slide 2 of 6 · Select the slide to view it at full size.
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead — slide 3 of 6
Slide 3 of 6 · Select the slide to view it at full size.
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead — slide 4 of 6
Slide 4 of 6 · Select the slide to view it at full size.
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead — slide 5 of 6
Slide 5 of 6 · Select the slide to view it at full size.
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead — slide 6 of 6
Slide 6 of 6 · Select the slide to view it at full size.