From ac6962ccd6b2bfe62cb115ed08bab0552338dbf6 Mon Sep 17 00:00:00 2001
From: PGFLMG <1106310035@qq.com>
Date: Sat, 2 Aug 2025 17:03:07 +0800
Subject: [PATCH] [Doc] Polish sgl-kernel readme for cu126 build error (#8704)

---
 sgl-kernel/README.md | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/sgl-kernel/README.md b/sgl-kernel/README.md
index c71b92335..72491433a 100644
--- a/sgl-kernel/README.md
+++ b/sgl-kernel/README.md
@@ -58,7 +58,15 @@ And if you build the sgl-kernel with cmake, you need to add `CMAKE_BUILD_PARALLE
 CMAKE_BUILD_PARALLEL_LEVEL=$(nproc) python -m uv build --wheel -Cbuild-dir=build --color=always .
 ```
 
-### FlashAttention on Hopper
+### ⚠️ Compilation Issue with `sgl-kernel` and CUDA 12.6
+
+When compiling `sgl-kernel` with FlashAttention on a Hopper GPU using CUDA 12.6, you may encounter a segmentation fault:
+
+```bash
+kernel/build/_deps/repo-flash-attention-src/hopper/instantiations/flash_fwd_hdimall_bf16_paged_softcap_sm90.cu -o CMakeFiles/flash_ops.dir/_deps/repo-flash-attention-src/hopper/instantiations/flash_fwd_hdimall_bf16_paged_softcap_sm90.cu.o
+Segmentation fault (core dumped)
+```
+
 ⚠️ **Note**: To ensure that FlashAttention compiles correctly on Hopper GPU Architecture(sm90), it is strongly [recommended](https://github.com/Dao-AILab/flash-attention/issues/1453) to use:
 - nvcc version: 12.6
 - ptxas version: 12.8