-
Notifications
You must be signed in to change notification settings - Fork 658
[bugfix][main]fix proxy decode bug #3750
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
Conversation
Signed-off-by: CHEN <[email protected]>
|
👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:
If CI fails, you can run linting and testing checks locally according Contributing and Testing. |
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.
Code Review
This pull request aims to fix a crash when decoding stream chunks that are not valid UTF-8. The proposed solution wraps the decoding in a try-except block. While this prevents the crash, it can lead to a corrupted data stream being sent to the client, as partial byte sequences might be yielded. My review includes critical feedback on this approach and suggests a more robust method for handling streaming text decoding to ensure stream integrity.
examples/disaggregated_prefill_v1/load_balance_proxy_layerwise_server_example.py
Show resolved
Hide resolved
Signed-off-by: CHEN <[email protected]>
Signed-off-by: CHEN <[email protected]>
### What this PR does / why we need it? fix proxy decode bug when parsing non-UTF-8 characters. - vLLM version: v0.11.0 - vLLM main: vllm-project/vllm@c9461e0 --------- Signed-off-by: CHEN <[email protected]> Signed-off-by: luolun <[email protected]>
### What this PR does / why we need it? fix proxy decode bug when parsing non-UTF-8 characters. - vLLM version: v0.11.0 - vLLM main: vllm-project/vllm@c9461e0 --------- Signed-off-by: CHEN <[email protected]> Signed-off-by: hwhaokun <[email protected]>
### What this PR does / why we need it? fix proxy decode bug when parsing non-UTF-8 characters. - vLLM version: v0.11.0 - vLLM main: vllm-project/vllm@c9461e0 --------- Signed-off-by: CHEN <[email protected]> Signed-off-by: nsdie <[email protected]>
### What this PR does / why we need it? fix proxy decode bug when parsing non-UTF-8 characters. - vLLM version: v0.11.0 - vLLM main: vllm-project/vllm@c9461e0 --------- Signed-off-by: CHEN <[email protected]>
What this PR does / why we need it?
fix proxy decode bug when parsing non-UTF-8 characters.
Does this PR introduce any user-facing change?
How was this patch tested?