From caebb83cef72065000c55817d57bfb7cf1d3f266 Mon Sep 17 00:00:00 2001
From: jianhua1724 <329212756@qq.com>
Date: Wed, 25 Mar 2026 09:52:32 +0800
Subject: [PATCH] feat(meta_schedule): expand CUDA unroll steps for SM70
 optimization

---
 src/s_tir/meta_schedule/schedule_rule/schedule_rule.cc | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/s_tir/meta_schedule/schedule_rule/schedule_rule.cc b/src/s_tir/meta_schedule/schedule_rule/schedule_rule.cc
index aa280b2e5b91..04a9a99eba5d 100644
--- a/src/s_tir/meta_schedule/schedule_rule/schedule_rule.cc
+++ b/src/s_tir/meta_schedule/schedule_rule/schedule_rule.cc
@@ -166,7 +166,7 @@ ffi::Array<ScheduleRule> ScheduleRule::DefaultCUDA() {
       ScheduleRule::ParallelizeVectorizeUnroll(
           /*max_jobs_per_core=*/-1,
           /*max_vectorize_extent=*/-1,
-          /*unroll_max_steps=*/ffi::Array<Integer>{0, 16, 64, 512, 1024},
+          /*unroll_max_steps=*/ffi::Array<Integer>{0, 16, 32, 64, 128, 256, 512, 1024},
           /*unroll_explicit=*/true),
       ScheduleRule::AutoBind(
           /*max_threadblocks=*/256,