diff --git a/docs/get_started/installation/iluvatar_gpu.md b/docs/get_started/installation/iluvatar_gpu.md
index 85c907e324..6f9514b2dc 100644
--- a/docs/get_started/installation/iluvatar_gpu.md
+++ b/docs/get_started/installation/iluvatar_gpu.md
@@ -1,4 +1,4 @@
-# Run ERNIE-4.5-300B-A47B model on iluvatar machine
+# Run ERNIE-4.5-300B-A47B & ERNIE-4.5-21B-A3B model on iluvatar machine
 The current version of the software merely serves as a demonstration demo for the Iluvatar CoreX combined with the Fastdeploy inference framework for large models. There may be issues when running the latest ERNIE4.5 model, and we will conduct repairs and performance optimization in the future. Subsequent versions will provide customers with a more stable version.
 
 ##  Machine Preparation
@@ -30,7 +30,7 @@ docker exec -it paddle_infer bash
 ```bash
 pip3 install paddlepaddle==3.1.0a0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
 pip3 install paddle-iluvatar-gpu==3.1.0 -i https://www.paddlepaddle.org.cn/packages/stable/ixuca/
-pip3 install fastdeploy -i https://www.paddlepaddle.org.cn/packages/stable/ixuca/ --extra-index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simplels
+pip3 install fastdeploy_iluvatar_gpu -i https://www.paddlepaddle.org.cn/packages/stable/ixuca/ --extra-index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simplels
 pip3 install aistudio-sdk==0.2.6
 ```
 
@@ -62,7 +62,7 @@ prompts = [
 sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=256)
 
 # load the model
-llm = LLM(model="/home/paddle/ernie-4_5-300b-a47b-bf16-paddle", tensor_parallel_size=16, max_model_len=8192)
+llm = LLM(model="/home/paddle/ernie-4_5-300b-a47b-bf16-paddle", tensor_parallel_size=16, max_model_len=8192, static_decode_blocks=0, quantization='wint8')
 
 # Perform batch inference
 outputs = llm.generate(prompts, sampling_params)
diff --git a/docs/zh/get_started/installation/iluvatar_gpu.md b/docs/zh/get_started/installation/iluvatar_gpu.md
index baeeaa6c63..2c5c8e9c45 100644
--- a/docs/zh/get_started/installation/iluvatar_gpu.md
+++ b/docs/zh/get_started/installation/iluvatar_gpu.md
@@ -1,4 +1,4 @@
-# 如何在天数机器上运行 ERNIE-4.5-300B-A47B-BF16
+# 如何在天数机器上运行 ERNIE-4.5-300B-A47B-BF16 & ERNIE-4.5-21B-A3B
 当前版本软件只是作为天数芯片 + Fastdeploy 推理大模型的一个演示 demo，跑最新ERNIE4.5模型可能存在问题，后续进行修复和性能优化，给客户提供一个更稳定的版本。
 
 ## 准备机器
@@ -29,7 +29,7 @@ docker exec -it paddle_infer bash
 ```bash
 pip3 install paddlepaddle==3.1.0a0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
 pip3 install paddle-iluvatar-gpu==3.1.0 -i https://www.paddlepaddle.org.cn/packages/stable/ixuca/
-pip3 install fastdeploy -i https://www.paddlepaddle.org.cn/packages/stable/ixuca/ --extra-index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simplels
+pip3 install fastdeploy_iluvatar_gpu -i https://www.paddlepaddle.org.cn/packages/stable/ixuca/ --extra-index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simplels
 pip3 install aistudio-sdk==0.2.6
 ```
 
@@ -62,7 +62,7 @@ prompts = [
 sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=256)
 
 # 加载模型
-llm = LLM(model="/home/paddle/ernie-4_5-300b-a47b-bf16-paddle", tensor_parallel_size=16, max_model_len=8192)
+llm = LLM(model="/home/paddle/ernie-4_5-300b-a47b-bf16-paddle", tensor_parallel_size=16, max_model_len=8192, static_decode_blocks=0, quantization='wint8')
 
 # 批量进行推理（llm内部基于资源情况进行请求排队、动态插入处理）
 outputs = llm.generate(prompts, sampling_params)