10 papers
A Graph-Based Analysis of Comparability, Scale, and Attribution in Private Transformer Inference
Souvik Das, Ariful Azad, Nitesh Saxena
Rising privacy concerns around large language models have accelerated research in private Transformer inference (PTI). Synthesizing the empirical claims in this line of research, h…
LLBPE: Linked-List Based GPU-Parallel BPE Tokenizer
Aditya Kovilur, Varun Chandra Shekar, Ariful Azad
Every LLM inference begins with tokenization, which converts raw input bytes into the discrete token sequence the model consumes. For text, this step is often implemented using Byt…
Lost in Conversation or Lost in Translation? Diagnosing Multi-Turn Degradation in RAG
Pranav Handa, Ariful Azad
When conversing with large language models (LLMs), users often begin with a simple question and build towards a multi-hop question through follow-up turns. Retrieval-augmented gene…
KGCache: Amortized Subgraph Retrieval for KG Reasoning with LLMs
Uros Stanic, Changcheng Yuan, Sabuj Laskar +1
Large language models can answer knowledge-intensive questions more reliably when they are grounded with knowledge graphs, but systems such as Think-on-Graph and Reasoning-on-Graph…
Sparsity-Aware Roofline Models for Sparse Matrix-Matrix Multiplication
Matthew Qian, Yahia Ramadan, Suhita Anubha +1
Sparse matrix-dense matrix multiplication (SpMM) is a critical kernel in scientific computing, graph analytics, and machine learning, whose performance is often constrained by memo…
Distributed-memory Algorithms for Sparse Matrix Permutation, Extraction, and Assignment
Elaheh Hassani, Md Taufique Hussain, Ariful Azad
We present scalable distributed-memory algorithms for sparse matrix permutation, extraction, and assignment. Our methods follow an Identify-Exchange-Build (IEB) strategy where each…
SparseTransX: Efficient Training of Translation-Based Knowledge Graph Embeddings Using Sparse Matrix Operations
Md Saidul Hoque Anik, Ariful Azad
Knowledge graph (KG) learning offers a powerful framework for generating new knowledge and making inferences. Training KG embedding can take a significantly long time, especially f…
Distributed-Memory Parallel Algorithms for Sparse Matrix and Sparse Tall-and-Skinny Matrix Multiplication
Isuru Ranawaka, Md Taufique Hussain, Charles Block +3
We consider a sparse matrix-matrix multiplication (SpGEMM) setting where one matrix is square and the other is tall and skinny. This special variant, called TS-SpGEMM, has importan…
Parallel Algorithms for Median Consensus Clustering in Complex Networks
Md Taufique Hussain, Mahantesh Halappanavar, Samrat Chatterjee +3
We develop an algorithm that finds the consensus of many different clustering solutions of a graph. We formulate the problem as a median set partitioning problem and propose a gree…
iSpLib: A Library for Accelerating Graph Neural Networks using Auto-tuned Sparse Operations
Md Saidul Hoque Anik, Pranav Badhe, Rohit Gampa +1
Core computations in Graph Neural Network (GNN) training and inference are often mapped to sparse matrix operations such as sparse-dense matrix multiplication (SpMM). These sparse…