-
-
Notifications
You must be signed in to change notification settings - Fork 10.8k
XGRAMMAR now support aarch64 #13894
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.
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
XGRAMMAR now support aarch64 #13894
Conversation
|
👋 Hi! Thank you for contributing to the vLLM project. 💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels. Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can either: Add 🚀 |
ceab9e2 to
ad9438f
Compare
|
@mgoin when will it be merged? |
|
your pre-commit is failing |
Signed-off-by: Johnny <[email protected]> Signed-off-by: johnnynunez <[email protected]>
Signed-off-by: Johnny <[email protected]> Signed-off-by: johnnynunez <[email protected]>
Signed-off-by: Johnny <[email protected]> Signed-off-by: johnnynunez <[email protected]>
Signed-off-by: Martin Hoyer <[email protected]> Signed-off-by: johnnynunez <[email protected]>
Signed-off-by: Jennifer Zhao <[email protected]> Signed-off-by: Roger Wang <[email protected]> Co-authored-by: Jennifer Zhao <[email protected]> Co-authored-by: Roger Wang <[email protected]> Signed-off-by: johnnynunez <[email protected]>
Signed-off-by: chaunceyjiang <[email protected]> Signed-off-by: johnnynunez <[email protected]>
Signed-off-by: johnnynunez <[email protected]>
done! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Your PR appears to have a lot of extra unintended changes, perhaps from a bad merge / rebase.
This update includes support for aarch64 among other fixes and improvements. Closes vllm-project#11886 Closes vllm-project#13986 Implements part of vllm-project#13894 Signed-off-by: Russell Bryant <[email protected]>
This update includes support for aarch64 among other fixes and improvements. Closes vllm-project#11886 Closes vllm-project#13986 Implements part of vllm-project#13894 Signed-off-by: Russell Bryant <[email protected]>
|
This will be addressed by #14868 |
This pull request includes updates to the
requirements-common.txtfile and modifications to thefallback_or_errorfunction in thevllm/model_executor/guided_decoding/__init__.pyfile. The changes aim to update dependencies and streamline the guided decoding process.Dependency updates:
requirements-common.txt: Updated thexgrammardependency to version 0.1.14.Guided decoding improvements:
vllm/model_executor/guided_decoding/__init__.py: Removed the fallback logic for non-x86 CPUs and the check forCpuArchEnum.X86in thefallback_or_errorfunction, simplifying the code and removing unnecessary platform-specific handling.