diff --git a/docs/Makefile b/docs/Makefile
index 50f77a30c09..13d81f4f847 100644
--- a/docs/Makefile
+++ b/docs/Makefile
@@ -19,7 +19,7 @@ compile:
 			echo "Executing $$nb"; \
 			jupyter nbconvert --to notebook --execute --inplace "$$nb" \
 				--ExecutePreprocessor.timeout=600 \
-				--ExecutePreprocessor.kernel_name=python3; \
+				--ExecutePreprocessor.kernel_name=python3 || exit 1; \
 		fi; \
 	done
 
diff --git a/docs/backend/native_api.ipynb b/docs/backend/native_api.ipynb
index 7207259ea3c..26758f7f975 100644
--- a/docs/backend/native_api.ipynb
+++ b/docs/backend/native_api.ipynb
@@ -220,19 +220,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# failed update with different parameter size\n",
+    "# failed update with different parameter size or wrong name\n",
     "\n",
     "url = \"http://localhost:30010/update_weights_from_disk\"\n",
-    "data = {\"model_path\": \"meta-llama/Llama-3.2-3B\"}\n",
+    "data = {\"model_path\": \"meta-llama/Llama-3.2-1B-wrong\"}\n",
     "\n",
     "response = requests.post(url, json=data)\n",
     "response_json = response.json()\n",
     "print_highlight(response_json)\n",
     "assert response_json[\"success\"] is False\n",
     "assert response_json[\"message\"] == (\n",
-    "    \"Failed to update weights: The size of tensor a (2048) must match \"\n",
-    "    \"the size of tensor b (3072) at non-singleton dimension 1.\\n\"\n",
-    "    \"Rolling back to original weights.\"\n",
+    "    \"Failed to get weights iterator: \"\n",
+    "    \"meta-llama/Llama-3.2-1B-wrong\"\n",
+    "    \" (repository not found).\"\n",
     ")"
    ]
   },
diff --git a/python/sglang/srt/server.py b/python/sglang/srt/server.py
index fc8ac150b3f..7b91cb69797 100644
--- a/python/sglang/srt/server.py
+++ b/python/sglang/srt/server.py
@@ -329,7 +329,7 @@ async def encode_request(obj: EmbeddingReqInput, request: Request):
         )
 
 
-@app.api_route("/encode", methods=["POST", "PUT"])
+@app.api_route("/classify", methods=["POST", "PUT"])
 @time_func_latency
 async def classify_request(obj: EmbeddingReqInput, request: Request):
     """Handle a reward model request. Now the arguments and return values are the same as embedding models."""