6 papers
FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow Matching
Divya Jyoti Bajpai, Shubham Agarwal, Apoorv Saxena +3
Flow Matching (FM) has recently emerged as a powerful approach for high-quality visual generation. However, their prohibitively slow inference due to a large number of denoising st…
Argus: Quality-Aware High-Throughput Text-to-Image Inference Serving System
Shubham Agarwal, Subrata Mitra, Saud Iqbal
Text-to-image (T2I) models have gained significant popularity. Most of these are diffusion models with unique computational characteristics, distinct from both traditional small-sc…
RCStat: A Statistical Framework for using Relative Contextualization in Transformers
Debabrata Mahapatra, Shubham Agarwal, Apoorv Saxena +1
Prior work on input-token importance in auto-regressive transformers has relied on Softmax-normalized attention weights, which obscure the richer structure of pre-Softmax query-key…
Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation
Shubham Agarwal, Sai Sundaresan, Subrata Mitra +6
Retrieval-Augmented Generation (RAG) is often used with Large Language Models (LLMs) to infuse domain knowledge or user-specific information. In RAG, given a user query, a retrieve…
Prompt-Aware Scheduling for Efficient Text-to-Image Inferencing System
Shubham Agarwal, Saud Iqbal, Subrata Mitra
Traditional ML models utilize controlled approximations during high loads, employing faster, but less accurate models in a process called accuracy scaling. However, this method is…
ScaleViz: Scaling Visualization Recommendation Models on Large Data
Ghazi Shazan Ahmad, Shubham Agarwal, Subrata Mitra +4
Automated visualization recommendations (vis-rec) help users to derive crucial insights from new datasets. Typically, such automated vis-rec models first calculate a large number o…