Typo ring memory weighted partitioning strategy

b897fa4420aef7ab114260da0569020bbee53703 · 2024-07-16 02:42:02 -0700 · Alex Cheema

Files touched

M README.md

Diff

commit b897fa4420aef7ab114260da0569020bbee53703
Author: Alex Cheema <41707476+AlexCheema@users.noreply.github.com>
Date:   Tue Jul 16 02:42:02 2024 -0700

    Typo ring memory weighted partitioning strategy
---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 5653b2e9..095ac29e 100644
--- a/README.md
+++ b/README.md
@@ -49,7 +49,7 @@ exo provides a ChatGPT-compatible API for running models. It's a one-line change
 
 Unlike other distributed inference frameworks, exo does not use a master-worker architecture. Instead, exo devices connect p2p. As long as a device is connected somewhere in the network, it can be used to run models.
 
-Exo supports different partitioning strategies to split up a model across devices. The default partitioning strategy is [ring memory weighted partitioning](exo/topology/ring_memory_weighted_partitioning.py). This runs an inference in a ring where each device runs a number of model layers proportional to the memory of the device.
+Exo supports different partitioning strategies 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.
 
 <picture>
   <img alt="ring topology" src="docs/ring-topology.png" width="30%" height="30%">

← 50d5e948 Update README.md · back to Exo · Fix broken links 9324fc15 →