[object Object]

← back to Exo

try screenshot without html

29a9156ea520a9ccf30faf2ac7cc3ecc16026fac · 2024-10-14 14:53:22 -0700 · Alex Cheema

Files touched

Diff

commit 29a9156ea520a9ccf30faf2ac7cc3ecc16026fac
Author: Alex Cheema <41707476+AlexCheema@users.noreply.github.com>
Date:   Mon Oct 14 14:53:22 2024 -0700

    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)
 <p>
     <picture>
         <img alt="A screenshot of exo running 5 nodes" src="docs/exo-screenshot.png" width="80%" height="80%">

← d43176de resize screenshot to 80%  ·  back to Exo  ·  remove redundant screenshot image in README 08ca7adc →