Expose max total num tokens from Runtime & Engine API (#2092)

docs/backend/native_api.ipynb

@@ -15,6 +15,7 @@
     "- `/health_generate`\n",
     "- `/flush_cache`\n",
     "- `/get_memory_pool_size`\n",
+    "- `/get_max_total_num_tokens`\n",
     "- `/update_weights`\n",
     "- `/encode`(embedding model)\n",
     "- `/classify`(reward model)\n",
@@ -201,6 +202,29 @@
     "print_highlight(response.text)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Get Maximum Total Number of Tokens\n",
+    "\n",
+    "Exposes the maximum number of tokens SGLang can handle based on the current configuration."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# get_max_total_num_tokens\n",
+    "\n",
+    "url = \"http://localhost:30010/get_max_total_num_tokens\"\n",
+    "\n",
+    "response = requests.get(url)\n",
+    "print_highlight(response.text)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},