Tiny add back missing router per attempt response metric#15621
Tiny add back missing router per attempt response metric#15621slin1237 merged 1 commit intosgl-project:mainfrom
Conversation
Summary of ChangesHello @fzyzcjy, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request addresses a missing metric recording in the SGLang model gateway's HTTP router. It ensures that every HTTP response attempt, including those within the retry logic, correctly logs its status code and an extracted error code. This enhancement is crucial for maintaining accurate observability and monitoring of the gateway's performance and error handling. Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
There was a problem hiding this comment.
Code Review
This pull request adds back a metric, smg_router_upstream_responses_total, to track upstream backend responses for each attempt within the HTTP router's retry logic. Note that the metric name in the code (smg_router_upstream_responses_total) differs slightly from the one in the pull request title (sgl_router_attempt_http_responses_total), but it is consistent with other metrics in the codebase. The change is correctly placed within the RetryExecutor's operation closure, ensuring that a metric is recorded for every attempt to route a request. The implementation is clean, correct, and improves the observability of the router's behavior. I have no further comments.
|
/tag-and-rerun-ci |
…n_eagle3_dp * 'main' of https://github.com/sgl-project/sglang: (208 commits) MoE: Skip SiLU/GELU activation for masked experts (sgl-project#15539) [GLM-ASR] GLM-ASR Support (sgl-project#15570) Improve engine customization interface (sgl-project#15635) chore: bump sgl-kernel version to 0.3.20 (sgl-project#15590) bugfix[schedule]: Refactor sort method and add related UT (sgl-project#13576) Adjust wrong `mtp` meaning introduce by mimo (sgl-project#15632) Tiny add back missing router per attempt response metric (sgl-project#15621) Fix router gRPC mode launch error caused by async loading (sgl-project#15368) [model-gateway] return 503 when all workers are circuit-broken (sgl-project#15611) [Diffusion] Support peak memory record in offline generate and serving (sgl-project#15610) [VLM] Tiny: Unify VLM environment variables (sgl-project#15572) [diffusion] chore: remove default post-denoising dit offload in local mode (sgl-project#15573) Tiny enable soft watchdog in CI for stuck without logs (sgl-project#15616) Tiny add stuck simulation (sgl-project#15613) Support soft watchdog for tokenizer/detokenizer/dp-controller processes (sgl-project#15607) Tiny avoid EnvField misuse (sgl-project#15612) add decode round robin policy (sgl-project#15164) Add glm-4.6-fp8 with/without mtp in nightly ci (sgl-project#15566) Adapt fixture-kit to gsm8k mixin (sgl-project#15599) [model-gateway] add retry support to OpenAI router chat endpoint (sgl-project#15589) ...
Motivation
Modifications
Accuracy Tests
Benchmarking and Profiling
Checklist