Support expert parallel in Transformers backend (#26162)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
Harry Mellor
2025-10-04 04:35:04 +00:00
committed by GitHub
co-authored by Isotr0py
parent ea507c3a93
commit d3d649efec
2 changed files with 32 additions and 21 deletions
+2 -1
View File
@@ -32,8 +32,9 @@ If the Transformers model implementation follows all the steps in [writing a cus
- All the features listed in the [compatibility matrix](../features/README.md#feature-x-feature)
- Any combination of the following vLLM parallelisation schemes:
- Data parallel
- Pipeline parallel
- Tensor parallel
- Expert parallel
- Pipeline parallel
Checking if the modeling backend is Transformers is as simple as: