From 3ff5c8f278f5adf459cfa54440f52a0297306513 Mon Sep 17 00:00:00 2001 From: Andrew Bringaze Linux Foundation Date: Thu, 26 Sep 2024 11:31:20 -0500 Subject: [PATCH] fix v3 --- _posts/2024-09-25-pytorch-native-architecture-optimization.md | 1 - 1 file changed, 1 deletion(-) diff --git a/_posts/2024-09-25-pytorch-native-architecture-optimization.md b/_posts/2024-09-25-pytorch-native-architecture-optimization.md index 58d685035b0f..1f219a49710d 100644 --- a/_posts/2024-09-25-pytorch-native-architecture-optimization.md +++ b/_posts/2024-09-25-pytorch-native-architecture-optimization.md @@ -4,7 +4,6 @@ title: "PyTorch Native Architecture Optimization: torchao" author: Team PyTorch --- - We’re happy to officially launch torchao, a PyTorch native library that makes models faster and smaller by leveraging low bit dtypes, quantization and sparsity. [torchao](https://github.com/pytorch/ao) is an accessible toolkit of techniques written (mostly) in easy to read PyTorch code spanning both inference and training. This blog will help you pick which techniques matter for your workloads. We benchmarked our techniques on popular GenAI models like LLama 3 and Diffusion models and saw minimal drops in accuracy. Unless otherwise noted the baselines are bf16 run on A100 80GB GPU.