5 papers
Sieve: Dynamic Expert-Aware PIM Acceleration for Evolving Mixture-of-Experts Models
Jungwoo Kim, Rubens Lacouture, Genghan Zhang +5
Mixture-of-Experts (MoE) has become a dominant architecture for scaling large language models (LLMs). However, the execution characteristics of MoE inference are changing rapidly a…
AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
Genghan Zhang, Shaowei Zhu, Anjiang Wei +6
We present AccelOpt, a self-improving large language model (LLM) agentic system that autonomously optimizes kernels for emerging AI acclerators, eliminating the need for expert-pro…
Streaming Tensor Programs: A Streaming Abstraction for Dynamic Parallelism
Gina Sohn, Genghan Zhang, Konstantin Hossfeld +5
Dynamic behaviors are becoming prevalent in tensor applications, like machine learning, where many widely used models contain data-dependent tensor shapes and control flow. However…
Adaptive Self-improvement LLM Agentic System for ML Library Development
Genghan Zhang, Weixin Liang, Olivia Hsu +1
ML libraries, often written in architecture-specific programming languages (ASPLs) that target domain-specific architectures, are key to efficient ML systems. However, writing thes…
Mixture-of-Mamba: Enhancing Multi-Modal State-Space Models with Modality-Aware Sparsity
Weixin Liang, Junhong Shen, Genghan Zhang +3
State Space Models (SSMs) have emerged as efficient alternatives to Transformers for sequential modeling, but their inability to leverage modality-specific features limits their pe…