[Hardware] Support platform-aware dependency routing#1040
Conversation
Signed-off-by: gcanlin <canlinguosdu@gmail.com> Co-authored-by: PopSoda2002 <zhouhp.me@gmail.com>
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 056101ebfb
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
@tjtanaa Do you have any more well-designed solution? 🤔 |
I have mentioned the necessity for non-CUDA non-CPU platform to use Is it ok that we use my PR instead? I have included everyone on coauthor list. |
|
Close as we co-work in #1046. |
PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.
Purpose
Close #997.
Test Plan
TODO
Test Result
Essential Elements of an Effective PR Description Checklist
supported_models.mdandexamplesfor a new model.BEFORE SUBMITTING, PLEASE READ https://github.com/vllm-project/vllm-omni/blob/main/CONTRIBUTING.md (anything written below this line will be removed by GitHub Actions)