diff --git a/docs/backend/speculative_decoding.ipynb b/docs/backend/speculative_decoding.ipynb
index afec9c4d51b7..011d8030b6a0 100644
--- a/docs/backend/speculative_decoding.ipynb
+++ b/docs/backend/speculative_decoding.ipynb
@@ -150,18 +150,11 @@
    "source": [
     "### EAGLE Decoding via Frequency-Ranked Speculative Sampling\n",
     "\n",
-    "By employing a truncated high-frequency token vocabulary in the draft model, Eagle speculative decoding reduces lm_head computational overhead while accelerating the pipeline without quality degradation.For more details checkout [this paper](https://arxiv.org/pdf/arXiv:2502.14856)\n",
+    "By employing a truncated high-frequency token vocabulary in the draft model, Eagle speculative decoding reduces lm_head computational overhead while accelerating the pipeline without quality degradation. For more details checkout [this paper](https://arxiv.org/pdf/arXiv:2502.14856)\n",
     "\n",
-    "Set `--speculative-token-map` to use this optimization. You can get the high-frequency token in FR-Spec from https://huggingface.co/thunlp/LLaMA3-Instruct-8B-FR-Spec. Or you can obtain high-frequency token by yourself.\n",
-    "+ Execute inference on your dataset using sglang's standard inference mode and persist the outputs.\n",
-    "+ Extract the top-k high-frequency tokens from the saved file. There is a reference implementation (https://gist.github.com/Zhou-sx/71a9196d2f324c93f79016579fdf57da). \n"
+    "Set `--speculative-token-map` to use this optimization. You can get the high-frequency token in FR-Spec from https://huggingface.co/thunlp/LLaMA3-Instruct-8B-FR-Spec. Or you can obtain high-frequency token by yourself (https://github.com/thunlp/FR-Spec/tree/main?tab=readme-ov-file#prepare-fr-spec-vocabulary-subset).\n"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": []
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -179,9 +172,9 @@
     "\n",
     "server_process, port = launch_server_cmd(\n",
     "    \"\"\"\n",
-    "python3 -m sglang.launch_server --model meta-llama/Llama-3.1-8B-Instruct  --speculative-algo EAGLE \\\n",
-    "    --speculative-draft lmzheng/sglang-EAGLE-LLaMA3-Instruct-8B --speculative-num-steps 3 \\\n",
-    "    --speculative-eagle-topk 4 --speculative-num-draft-tokens 16 --speculative-token-map {hot_token_ids.pt} \n",
+    "python3 -m sglang.launch_server --model meta-llama/Meta-Llama-3-8B-Instruct --speculative-algo EAGLE \\\n",
+    "    --speculative-draft lmzheng/sglang-EAGLE-LLaMA3-Instruct-8B --speculative-num-steps 5 \\\n",
+    "    --speculative-eagle-topk 8 --speculative-num-draft-tokens 64 --speculative-token-map {hot_token_ids.pt} \n",
     "\"\"\"\n",
     ")\n",
     "\n",
@@ -199,7 +192,7 @@
     "client = openai.Client(base_url=f\"http://127.0.0.1:{port}/v1\", api_key=\"None\")\n",
     "\n",
     "response = client.chat.completions.create(\n",
-    "    model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n",
+    "    model=\"meta-llama/Meta-Llama-3-8B-Instruct\",\n",
     "    messages=[\n",
     "        {\"role\": \"user\", \"content\": \"List 3 countries and their capitals.\"},\n",
     "    ],\n",