Author

David Limpus

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Jun 2026

UltraQuant: 4-bit KV Caching for Context-Heavy Agents

This work frames 4-bit KV caching around multi-round agent workloads where task quality, cache residency, and serving throughput must be measured jointly, and presents serving optimizations on AMD GPUs, including optimized decode-attention kernels and UltraQuant.

Inesh Chakrabarti, David Limpus, Aditi Rana et al. · arXiv.org · 0 citations