alihan/exo
1
0
Fork 0
mirror of https://github.com/exo-explore/exo.git synced 2025-10-23 02:57:14 +03:00
Code Issues Packages Projects Releases Wiki Activity

try screenshot without html

Browse Source
This commit is contained in:
Alex Cheema
2024-10-14 14:53:22 -07:00
committed by GitHub
parent d43176de9c
commit 29a9156ea5
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@@ -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%">