From f6cd628cd8099b4d6d1d671b8f462a3149299237 Mon Sep 17 00:00:00 2001
From: Xiangyu Tian <109123695+xiangyuT@users.noreply.github.com>
Date: Tue, 18 Jun 2024 16:50:48 +0800
Subject: [PATCH] Fix script usage in vLLM CPU Quickstart (#11353)

---
 .../vllm_cpu_docker_quickstart.md             | 20 ++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/docs/readthedocs/source/doc/LLM/DockerGuides/vllm_cpu_docker_quickstart.md b/docs/readthedocs/source/doc/LLM/DockerGuides/vllm_cpu_docker_quickstart.md
index 36b39ed5..d5b14000 100644
--- a/docs/readthedocs/source/doc/LLM/DockerGuides/vllm_cpu_docker_quickstart.md
+++ b/docs/readthedocs/source/doc/LLM/DockerGuides/vllm_cpu_docker_quickstart.md
@@ -115,4 +115,22 @@ wrk -t8 -c8 -d15m -s payload-1024.lua http://localhost:8000/v1/completions --tim
 
 #### Offline benchmark through benchmark_vllm_throughput.py
 
-Please refer to this [section](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/vLLM_quickstart.html#performing-benchmark) on how to use `benchmark_vllm_throughput.py` for benchmarking.
+```bash
+cd /llm
+wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
+
+source ipex-llm-init -t
+export MODEL="YOUR_MODEL"
+
+python3 ./benchmark_vllm_throughput.py \
+    --backend vllm \
+    --dataset ./ShareGPT_V3_unfiltered_cleaned_split.json \
+    --model $MODEL \
+    --num-prompts 1000 \
+    --seed 42 \
+    --trust-remote-code \
+    --enforce-eager \
+    --dtype bfloat16 \
+    --device cpu \
+    --load-in-low-bit bf16
+```
\ No newline at end of file