4 papers
FastLane: Efficient Routed Systems for Late-Interaction Retrieval
Ramnath Kumar, Prateek Jain, Cho-Jui Hsieh
Late-interaction retrieval models like ColBERT achieve superior accuracy by enabling token-level interactions, but their computational cost hinders scalability and integration with…
Matryoshka Model Learning for Improved Elastic Student Models
Chetan Verma, Aditya Srinivas Timmaraju, Cho-Jui Hsieh +7
Industry-grade ML models are carefully designed to meet rapidly evolving serving constraints, which requires significant resources for model development. In this paper, we propose…
Compressing Many-Shots in In-Context Learning
Devvrit Khatri, Pranamya Kulkarni, Nilesh Gupta +9
Large Language Models (LLMs) have been shown to be able to learn different tasks without explicit finetuning when given many input-output examples / demonstrations through In-Conte…
Matryoshka Quantization
Pranav Nair, Puranjay Datta, Jeff Dean +2
Quantizing model weights is critical for reducing the communication and inference costs of large models. However, quantizing models -- especially to low precisions like int4 or int…