diff --git a/benchmark/deepseek_v3/README.md b/benchmark/deepseek_v3/README.md
index ea972831a..387a6629f 100644
--- a/benchmark/deepseek_v3/README.md
+++ b/benchmark/deepseek_v3/README.md
@@ -31,7 +31,7 @@ For high QPS scenarios, add the `--enable-dp-attention` argument to boost throug
 ### Using pip
 ```bash
 # Installation
-pip install "sglang[all]>=0.4.1.post5" --find-links https://flashinfer.ai/whl/cu124/torch2.4/flashinfer
+pip install "sglang[all]>=0.4.2.post2" --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer
 
 # Launch
 python3 -m sglang.launch_server --model deepseek-ai/DeepSeek-V3 --tp 8 --trust-remote-code