From 06a1656e02090d6da15427a6c0427c8c3c869dc0 Mon Sep 17 00:00:00 2001
From: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
Date: Wed, 16 Apr 2025 14:27:34 +0800
Subject: [PATCH] [doc] Update benchmark_and_profiling.md (#5449)

---
 docs/references/benchmark_and_profiling.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/docs/references/benchmark_and_profiling.md b/docs/references/benchmark_and_profiling.md
index 37c45457f..67daa8db5 100644
--- a/docs/references/benchmark_and_profiling.md
+++ b/docs/references/benchmark_and_profiling.md
@@ -64,6 +64,8 @@
 
   This command sets the number of prompts to 2 with `--num-prompts` argument and limits the length of output sequences to 100 with `--sharegpt-output-len` argument, which can generate a small trace file for browser to open smoothly.
 
+  Additionally, if you want to locate the SGLang Python source code through the cuda kernel in Trace, you need to disable CUDA Graph when starting the service. This can be done by using the `--disable-cuda-graph` parameter in the command to start the service.
+
 ## Profile with Nsight
 
 [Nsight systems](https://docs.nvidia.com/nsight-systems/) is an advanced tool that exposes more profiling details, such as register and shared memory usage, annotated code regions and low-level CUDA APIs and events.