4 papers · 1 filter
CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs
Han Guo, Jack Zhang, Arjun Menon +4
Transformer training systems are built around dense linear algebra, yet a nontrivial fraction of end-to-end time is spent on surrounding memory-bound operators. Normalization, acti…
TorchAO: PyTorch-Native Training-to-Serving Model Optimization
Andrew Or, Apurva Jain, Daniel Vega-Myhre +10
We present TorchAO, a PyTorch-native model optimization framework leveraging quantization and sparsity to provide an end-to-end, training-to-serving workflow for AI models. TorchAO…
Characterizing and Efficiently Accelerating Multimodal Generation Model Inference
Yejin Lee, Anna Sun, Basil Hosmer +27
Generative artificial intelligence (AI) technology is revolutionizing the computing industry. Not only its applications have broadened to various sectors but also poses new system…
Flex Attention: A Programming Model for Generating Optimized Attention Kernels
Juechu Dong, Boyuan Feng, Driss Guessous +2
Over the past 7 years, attention has become one of the most important primitives in deep learning. The primary approach to optimize attention is FlashAttention, which fuses the ope…