From 29a9156ea520a9ccf30faf2ac7cc3ecc16026fac Mon Sep 17 00:00:00 2001 From: Alex Cheema <41707476+AlexCheema@users.noreply.github.com> Date: Mon, 14 Oct 2024 14:53:22 -0700 Subject: [PATCH] try screenshot without html --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 557e1575..0d5d963a 100644 --- a/README.md +++ b/README.md @@ -58,6 +58,7 @@ Unlike other distributed inference frameworks, exo does not use a master-worker Exo supports different [partitioning strategies](exo/topology/partitioning_strategy.py) to split up a model across devices. The default partitioning strategy is [ring memory weighted partitioning](exo/topology/ring_memory_weighted_partitioning_strategy.py). This runs an inference in a ring where each device runs a number of model layers proportional to the memory of the device. +!["A screenshot of exo running 5 nodes](docs/exo-screenshot.png)

A screenshot of exo running 5 nodes