Skip to content

Commit 096ab4a

Browse files
space addition (#1747)
1 parent 0f4e309 commit 096ab4a

File tree

1 file changed

+1
-0
lines changed

1 file changed

+1
-0
lines changed

_posts/2024-09-26-pytorch-native-architecture-optimization.md

+1
Original file line numberDiff line numberDiff line change
@@ -4,6 +4,7 @@ title: "PyTorch Native Architecture Optimization: torchao"
44
author: Team PyTorch
55
---
66

7+
78
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.
89

910
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.

0 commit comments

Comments
 (0)