10 papers
Understanding and Improving Communication Performance in Multi-node LLM Inference
Prajwal Singhania, Siddharth Singh, Lannie Dalton Hough +4
As large language models (LLMs) continue to grow in size, distributed inference has become increasingly important. Model-parallel strategies must now efficiently scale not only acr…
Record-Remix-Replay: Hierarchical GPU Kernel Optimization using Evolutionary Search
Daniel Nichols, Konstantinos Parasyris, Caetano Melone +3
As high-performance computing and AI workloads become increasingly dependent on GPUs, maintaining high performance across rapidly evolving hardware generations has become a major c…
Optimizing Agentic Language Model Inference via Speculative Tool Calls
Daniel Nichols, Prajwal Singhania, Charles Jekel +2
Language models (LMs) are becoming increasingly dependent on external tools. LM-based agentic frameworks frequently interact with their environment via such tools to search files,…
Counting Without Running: Evaluating LLMs' Reasoning About Code Complexity
Gregory Bolet, Giorgis Georgakoudis, Konstantinos Parasyris +4
Modern GPU software stacks demand developers who can anticipate performance bottlenecks before ever launching a kernel; misjudging floating-point workloads upstream can derail tuni…
LLMs as Packagers of HPC Software
Caetano Melone, Daniel Nichols, Konstantinos Parasyris +2
High performance computing (HPC) software ecosystems are inherently heterogeneous, comprising scientific applications that depend on hundreds of external packages, each with distin…
Integrating Performance Tools in Model Reasoning for GPU Kernel Optimization
Daniel Nichols, Konstantinos Parasyris, Charles Jekel +2
Language models are now prevalent in software engineering with many developers using them to automate tasks and accelerate their development. While language models have been tremen…