diff --git a/.github/workflows/pr-test-xpu.yml b/.github/workflows/pr-test-xpu.yml
index fb391ea01..ddf9c7f70 100644
--- a/.github/workflows/pr-test-xpu.yml
+++ b/.github/workflows/pr-test-xpu.yml
@@ -27,8 +27,8 @@ jobs:
         with:
           filters: |
             main_package:
-              - "python/**"
-              - "!python/sglang/multimodal_gen/**"
+              - "python/sglang/!(multimodal_gen)/**"
+              - "python/*.toml"
               - "scripts/ci/**"
               - "test/**"
               - "sgl-kernel/**"
diff --git a/sgl-router/README.md b/sgl-router/README.md
index d6d751b00..d9036c4d1 100644
--- a/sgl-router/README.md
+++ b/sgl-router/README.md
@@ -41,6 +41,7 @@ High-performance model routing control and data plane for large-scale LLM deploy
 ## Documentation
 - **User Guide**: [docs.sglang.ai/advanced_features/router.html](https://docs.sglang.ai/advanced_features/router.html)
 - Additional guides, API references, and deployment patterns are continuously updated alongside SGLang releases.
+- **Tokenizer Module**: See [src/tokenizer/README.md](src/tokenizer/README.md) for tokenizer architecture and chat template support.
 
 ## Installation
 ### Prerequisites