From 1f9d65f57d08bd5495cd399ba1163925b843071c Mon Sep 17 00:00:00 2001
From: strgrb <zhangkaihong.zkh@antgroup.com>
Date: Fri, 15 Aug 2025 13:19:56 +0800
Subject: [PATCH] use fast math for per_token_group_quant_8bit. (#9177)

Co-authored-by: Zhang Kaihong <zhangkaihong.zkh@alibaba-inc.com>
---
 sgl-kernel/CMakeLists.txt | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sgl-kernel/CMakeLists.txt b/sgl-kernel/CMakeLists.txt
index 4b9732cce..ddf57a749 100644
--- a/sgl-kernel/CMakeLists.txt
+++ b/sgl-kernel/CMakeLists.txt
@@ -301,6 +301,8 @@ target_include_directories(common_ops PRIVATE
     ${repo-cutlass_SOURCE_DIR}/examples/common
     ${repo-flash-attention_SOURCE_DIR}/csrc/flash_attn/src
 )
+set_source_files_properties("csrc/gemm/per_token_group_quant_8bit" PROPERTIES COMPILE_OPTIONS "--use_fast_math")
+
 
 find_package(Python3 COMPONENTS Interpreter REQUIRED)
 execute_process(