Arnab Raha
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Architecture×1
Frequent co-authors
Research Timeline
2026
SPARQLe: Sub-Precision Activation Representation for Quantized LLM Inference
SPARQLe is a hardware-software co-design framework that exploits the inherent sub-precision sparsity of LLM activations to reduce memory traffic and enable efficient computation on lower-bit datapaths, significantly accelerating inference.
Highlighted terms show continued research focus across papers