4 citations · 4 across the 4 of their papers we have counts for
4 papers
Fast Collection Operations from Indexed Stream Fusion
Scott Kovach, Praneeth Kolichala, Kyle A. Miller +2
We present a system of efficient methods for traversing and combining associative collection data structures. A distinguishing feature of the system is that, like traditional seque…
Scorch: A Library for Sparse Deep Learning
Bobby Yan, Alexander J. Root, Trevor Gale +2
The rapid growth in the size of deep learning models strains the capabilities of traditional dense computation paradigms. Leveraging sparse computation has become increasingly popu…
Automatic Tracing in Task-Based Runtime Systems
Rohan Yadav, Michael Bauer, David Broman +3
Implicitly parallel task-based runtime systems often perform dynamic analysis to discover dependencies in and extract parallelism from sequential programs. Dependence analysis beco…
Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs
Krista Opsahl-Ong, Michael J Ryan, Josh Purtell +4
Language Model Programs, i.e. sophisticated pipelines of modular language model (LM) calls, are increasingly advancing NLP tasks, but they require crafting prompts that are jointly…