5 papers
Serving Masked Diffusion LLMs: Characterization and Design Principles from Real Hardware
Farhana Amin, Sabiha Afroz, Mona Moghadampanah +1
Masked diffusion language models (dLLMs) can in principle generate text faster than autoregressive (AR) models, since they denoise many tokens at once. Recent systems have begun bu…
CAI-DLLM: Convergence Aware Inference for Diffusion Language Models
Farhana Amin, Sabiha Afroz, Dimitrios S. Nikolopoulos
Diffusion language models can generate many tokens in parallel, but they still require repeated denoising steps during inference. This makes generation costly, especially when the…
Modality Inflation: Energy Characterization and Optimization Opportunities for MLLM Inference
Mona Moghadampanah, Adib Rezaei Shahmirzadi, Farhana Amin +1
Multimodal large language models (MLLMs) are built on text-only LLMs by incorporating additional modalities, enabling multimodal understanding and a broader range of applications.…
DiffPro: Joint Timestep and Layer-Wise Precision Optimization for Efficient Diffusion Inference
Farhana Amin, Sabiha Afroz, Kanchon Gharami +2
Diffusion models produce high quality images but inference is costly due to many denoising steps and heavy matrix operations. We present DiffPro, a post-training, hardware-faithful…
MARCO: Multi-Agent Code Optimization with Real-Time Knowledge Integration for High-Performance Computing
Asif Rahman, Veljko Cvetkovic, Kathleen Reece +7
Large language models (LLMs) have transformed software development through code generation capabilities, yet their effectiveness for high-performance computing (HPC) remains limite…