-
-
Notifications
You must be signed in to change notification settings - Fork 5.4k
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
[Hardware][Gaudi][Bugfix] Fix error for guided decoding #12317
base: main
Are you sure you want to change the base?
Conversation
👋 Hi! Thank you for contributing to the vLLM project. 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 do one of these:
🚀 |
vllm/model_executor/guided_decoding/outlines_logits_processors.py
Outdated
Show resolved
Hide resolved
db981c2
to
ca1b788
Compare
/ready |
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.
LGTM. possible to add a test in hpu ci?
Added |
Signed-off-by: zhouyu5 <[email protected]>
Signed-off-by: zhouyu5 <[email protected]>
Signed-off-by: zhouyu5 <[email protected]>
Signed-off-by: zhouyu5 <[email protected]>
This reverts commit 38d4713. Signed-off-by: zhouyu5 <[email protected]>
27e6fa1
to
f5caa08
Compare
Revert ci test due to out of memory error. |
@zhouyu5 can you please merge with main to fix CI? |
It fixes the error on Gaudi when enabling guided decoding:
RuntimeError: synNodeCreateWithId failed for node: strided_insert with synStatus 1 [Invalid argument]
After fix, all UT have passed for guided decoding and tool calling, including:
vllm-fork/tests/entrypoints/llm/test_guided_generate.py vllm-fork/tests/tool_use/*.py