[Bug] Fix outdated links in source code (#35314)

Signed-off-by: yewentao256 <zhyanwentao@126.com>

.github/mergify.yml

@@ -259,8 +259,7 @@ pull_request_rules:
       - files=benchmarks/run_structured_output_benchmark.sh
       - files=docs/features/structured_outputs.md
       - files=examples/offline_inference/structured_outputs.py
-      - files=examples/online_serving/openai_chat_completion_structured_outputs.py
-      - files=examples/online_serving/openai_chat_completion_structured_outputs_with_reasoning.py
+      - files=examples/online_serving/structured_outputs/structured_outputs.py
       - files~=^tests/v1/structured_output/
       - files=tests/v1/entrypoints/llm/test_struct_output_generate.py
       - files~=^vllm/v1/structured_output/

docs/design/metrics.md

@@ -656,7 +656,7 @@ vLLM has support for OpenTelemetry tracing:
 - Added by <https://github.com/vllm-project/vllm/pull/4687> and reinstated by <https://github.com/vllm-project/vllm/pull/20372>
 - Configured with `--oltp-traces-endpoint` and `--collect-detailed-traces`
 - [OpenTelemetry blog post](https://opentelemetry.io/blog/2024/llm-observability/)
-- [User-facing docs](../examples/online_serving/opentelemetry.md)
+- [User-facing docs](../../examples/online_serving/opentelemetry/README.md)
 - [Blog post](https://medium.com/@ronen.schaffer/follow-the-trail-supercharging-vllm-with-opentelemetry-distributed-tracing-aa655229b46f)
 - [IBM product docs](https://www.ibm.com/docs/en/instana-observability/current?topic=mgaa-monitoring-large-language-models-llms-vllm-public-preview)
 

tools/profiler/print_layerwise_table.py

@@ -33,7 +33,10 @@ if __name__ == "__main__":
         "--json-trace",
         type=str,
         required=True,
-        help="json trace file output by examples/offline_inference/profiling.py",
+        help=(
+            "JSON trace file generated by scripts that use "
+            "vllm.profiler.layerwise_profile"
+        ),
     )
     parser.add_argument(
         "--phase",

tools/profiler/visualize_layerwise_profile.py

@@ -564,8 +564,10 @@ if __name__ == "__main__":
         "--json-trace",
         type=str,
         required=True,
-        help="json trace file output by \
-                              examples/offline_inference/profiling.py",
+        help=(
+            "JSON trace file generated by scripts that use "
+            "vllm.profiler.layerwise_profile"
+        ),
     )
     parser.add_argument(
         "--output-directory", type=str, required=False, help="Directory to output plots"

vllm/model_executor/models/config.py

@@ -213,7 +213,7 @@ class NomicBertModelConfig(VerifyAndUpdateConfig):
                     "Nomic context extension is disabled. "
                     "Changing max_model_len from %s to %s. "
                     "To enable context extension, see: "
-                    "https://github.com/vllm-project/vllm/tree/main/examples/offline_inference/context_extension.html",
+                    "https://github.com/vllm-project/vllm/tree/main/examples/offline_inference/context_extension.py",
                     max_model_len_before,
                     model_config.max_model_len,
                 )