Skip to content

[Doc][Model] Add principles of modeling files in vllm-ascend #4327

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
+5 −0
Closed

[Doc][Model] Add principles of modeling files in vllm-ascend #4327

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions vllm_ascend/models/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
# Principles of Modeling files in vllm-ascend

To keep a more concise software architecture and avoid maintaining a wide variety of models, vllm-ascend will not maintain any modeling files in the future, instead we just register and replace some `CustomOp` in vllm to support the model inference on Ascend devices.

Currently, we plan to remove all the VL modeling files, find more details at [#4084](https://github.com/vllm-project/vllm-ascend/issues/4084).
Loading