4 papers
CeQe: Grounding Lexical Retrieval in Semantic Evidence
Adam Kahirov, Umesh Deshpande, Swaminathan Sundararaman
Lexical retrieval (BM25) captures exact keyword matches and weights terms by corpus-wide significance, but it is blind to the semantic vocabulary gap: when a relevant document phra…
Hierarchical BM25: Lexical Search at Billion-Document Scale
Umesh Deshpande, Swaminathan Sundararaman
A flat BM25 index over one billion documents occupies about 400 GB. Holding it in memory requires DRAM proportional to corpus size. Serving it from disk takes 4-12 seconds per quer…
Symbiosis: Multi-Adapter Inference and Fine-Tuning
Saransh Gupta, Umesh Deshpande, Travis Janssen +1
Parameter-efficient fine-tuning (PEFT) allows model builders to capture the task-specific parameters into adapters, which are a fraction of the size of the original base model. Pop…
ZipNN: Lossless Compression for AI Models
Moshik Hershcovitch, Andrew Wood, Leshem Choshen +7
With the growth of model sizes and the scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While th…