[Hotfix] Fix model policy matching strategy in ShardFormer (#5064)

* hotfix/Fix get model policy strategy in ShardFormer

* fix bug in auto policy
This commit is contained in:
Zhongkai Zhao
2023-11-22 11:19:39 +08:00
committed by GitHub
parent 4ccb9ded7d
commit 75af66cd81
4 changed files with 8 additions and 42 deletions

View File

@@ -32,7 +32,7 @@ Colossal Inference is composed of three main components:
In this section we discuss how the colossal inference works and integrates with the `Shardformer` . The details can be found in our codes.
![Colossal-Inference](https://raw.githubusercontent.com/hpcaitech/public_assets/main/colossalai/img/inference/inference-arch.png)
<img src="https://raw.githubusercontent.com/hpcaitech/public_assets/main/colossalai/img/inference/inference-arch.png" alt="Colossal-Inference" style="zoom: 33%;"/>
## Roadmap of our implementation