173 citations · 782 across the 61 of their papers we have counts for
64 papers
Unifying In-Memory Data Analytics through Sparse Compilation
Anand Jayarajan, Gennady Pekhimenko
As modern data analytics workloads become increasingly heterogeneous and hardware-intensive, achieving efficient multi-core performance across diverse applications remains an open…
ArbiGraph: Arbitrarily Scalable Verifiable Task Graphs for Evaluating Context Management
Pavel Golikov, Evgenii Opryshko, Gennady Pekhimenko +1
We introduce ARBIGRAPH, a benchmark generator for evaluating whether tool-assisted language agents can retain, update, compose, and discard task-relevant context across extended re…
SpecBench: Evaluating Specification-Level Reasoning for Software Engineering LLM Agents
Grant Hamblin, Kevin Song, Zhanda Zhu +4
Software engineering (SWE) agents are transitioning from code generation to full software development lifecycle automation. A critical phase in this lifecycle is specification desi…
Robust Reasoning Benchmark
Pavel Golikov, Evgenii Opryshko, Gennady Pekhimenko +1
While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their problem-solving abilities depend on the context and textual formatting. We in…
BHCast: Unlocking Black Hole Plasma Dynamics from a Single Blurry Image with Long-Term Forecasting
Renbo Tu, Ali SaraerToosi, Nicholas S. Conroy +2
The Event Horizon Telescope (EHT) delivered the first image of a black hole by capturing the light from its surrounding accretion flow, revealing structure but not dynamics. Simula…
SwiftFusion: Scalable Sequence Parallelism for Distributed Inference of Diffusion Transformers on GPUs
Jiacheng Yang, Jun Wu, Yaoyao Ding +3
Diffusion Transformers (DiTs) have gained increasing adoption in high-quality image and video generation. As demand for higher-resolution images and longer videos increases, single…
DCC: Data-Centric Compilation of Machine Learning Kernels for Processing-In-Memory Architectures
Peiming Yang, Sankeerth Durvasula, Ivan Fernandez +4
High-performance Host processors can integrate Processing-In-Memory (PIM) devices, which can accelerate memory-intensive kernels of Machine Learning (ML) models, including Large La…
What Limits Agentic Systems Efficiency?
Song Bian, Minghao Yan, Anand Jayarajan +2
Large Language Models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated strong reasoning capabilities. To further enhance LLM capabilities, recent agentic systems, such…
LoRAFusion: Efficient LoRA Fine-Tuning for LLMs
Zhanda Zhu, Qidong Su, Yaoyao Ding +3
Low-Rank Adaptation (LoRA) has become the leading Parameter-Efficient Fine-Tuning (PEFT) method for Large Language Models (LLMs), as it significantly reduces GPU memory usage while…
DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling
Yubo Gao, Renbo Tu, Gennady Pekhimenko +1
Differentially-Private SGD (DP-SGD) and its adaptive variant DP-Adam are powerful techniques to protect user privacy when using sensitive data to train neural networks. During trai…
Aegis: Taxonomy and Optimizations for Overcoming Agent-Environment Failures in LLM Agents
Kevin Song, Anand Jayarajan, Yaoyao Ding +4
Large Language Models (LLMs) agents augmented with domain tools promise to autonomously execute complex tasks requiring human-level intelligence, such as customer service and digit…
TypyBench: Evaluating LLM Type Inference for Untyped Python Repositories
Honghua Dong, Jiacheng Yang, Xun Deng +4
Type inference for dynamic languages like Python is a persistent challenge in software engineering. While large language models (LLMs) have shown promise in code understanding, the…
Hexcute: A Compiler Framework for Automating Layout Synthesis in GPU Programs
Xiao Zhang, Yaoyao Ding, Bolin Sun +3
Efficient GPU programming is crucial for achieving high performance in deep learning (DL) applications. The performance of GPU programs depends on how data is parallelized across t…
Tilus: A Tile-Level GPGPU Programming Language for Low-Precision Computation
Yaoyao Ding, Bohan Hou, Xiao Zhang +5
Serving Large Language Models (LLMs) is critical for AI-powered applications, yet it demands substantial computational resources, particularly in memory bandwidth and computational…
Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization
Zhanda Zhu, Christina Giannoula, Muralidhar Andoorveedu +4
Various parallelism, such as data, tensor, and pipeline parallelism, along with memory optimizations like activation checkpointing, redundancy elimination, and offloading, have bee…
Seesaw: High-throughput LLM Inference via Model Re-sharding
Qidong Su, Wei Zhao, Xin Li +6
To improve the efficiency of distributed large language model (LLM) inference, various parallelization strategies, such as tensor and pipeline parallelism, have been proposed. Howe…
Tally: Non-Intrusive Performance Isolation for Concurrent Deep Learning Workloads
Wei Zhao, Anand Jayarajan, Gennady Pekhimenko
GPU underutilization is a significant concern in many production deep learning clusters, leading to prolonged job queues and increased operational expenses. A promising solution to…
APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts
Honghua Dong, Qidong Su, Yubo Gao +5
Large Language Models (LLMs) have become increasingly capable of handling diverse tasks with the aid of well-crafted prompts and integration of external tools, but as task complexi…
Proteus: Preserving Model Confidentiality during Graph Optimizations
Yubo Gao, Maryam Haghifam, Christina Giannoula +3
Deep learning (DL) models have revolutionized numerous domains, yet optimizing them for computational efficiency remains a challenging endeavor. Development of new DL models typica…
PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory Architectures
Christina Giannoula, Peiming Yang, Ivan Fernandez +7
Graph Neural Networks (GNNs) are emerging ML models to analyze graph-structure data. Graph Neural Network (GNN) execution involves both compute-intensive and memory-intensive kerne…
Minuet: Accelerating 3D Sparse Convolutions on GPUs
Jiacheng Yang, Christina Giannoula, Jun Wu +3
Sparse Convolution (SC) is widely used for processing 3D point clouds that are inherently sparse. Different from dense convolution, SC preserves the sparsity of the input point clo…
HybridTier: an Adaptive and Lightweight CXL-Memory Tiering System
Kevin Song, Jiacheng Yang, Zixuan Wang +3
Modern workloads are demanding increasingly larger memory capacity. Compute Express Link (CXL)-based memory tiering has emerged as a promising solution for addressing this problem…
TorchProbe: Fuzzing Dynamic Deep Learning Compilers
Qidong Su, Chuqin Geng, Gennady Pekhimenko +1
Static and dynamic computational graphs represent two distinct approaches to constructing deep learning frameworks. The former prioritizes compiler-based optimizations, while the l…
The Synergy of Speculative Decoding and Batching in Serving Large Language Models
Qidong Su, Christina Giannoula, Gennady Pekhimenko
Large Language Models (LLMs) like GPT are state-of-the-art text generation models that provide significant assistance in daily routines. However, LLM execution is inherently sequen…