From 83de0d9b08efcc0d086f7e6e5a986155c0b60f1f Mon Sep 17 00:00:00 2001
From: Kaihui-intel <kaihui.tang@intel.com>
Date: Mon, 13 Oct 2025 23:06:44 -0400
Subject: [PATCH 1/2] fix rtn tuning_device

Signed-off-by: Kaihui-intel <kaihui.tang@intel.com>
---
 auto_round/compressors/base.py       |  2 +-
 test/test_cuda/test_multiple_card.py | 13 +++++++++++++
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/auto_round/compressors/base.py b/auto_round/compressors/base.py
index 48cf0cd1a..8ceaefc00 100644
--- a/auto_round/compressors/base.py
+++ b/auto_round/compressors/base.py
@@ -1422,7 +1422,7 @@ def _quantize_layer_via_rtn(self, name: str) -> None:
             m.zp = None
         else:
             try:
-                m = m.to(self.device)
+                m = m.to(m.tuning_device if hasattr(m, "tuning_device") else self.device)
                 m = WrapperLinear(
                     m,
                     enable_minmax_tuning=False,
diff --git a/test/test_cuda/test_multiple_card.py b/test/test_cuda/test_multiple_card.py
index ad33f071b..43e67e957 100644
--- a/test/test_cuda/test_multiple_card.py
+++ b/test/test_cuda/test_multiple_card.py
@@ -241,6 +241,19 @@ def test_device_map_dict(self):
             device_map=device_map,
         )
         autoround.quantize()
+        
+        # test rtn
+        autoround = AutoRound(
+            model_name,
+            tokenizer,
+            bits=bits,
+            group_size=group_size,
+            sym=sym,
+            iters=0,
+            seqlen=2,
+            device_map=device_map,
+        )
+        autoround.quantize()
 
     @multi_card
     @require_greater_than_050

From 0719221137e49a0fa85841edc36e57e4c767be50 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Tue, 14 Oct 2025 03:09:00 +0000
Subject: [PATCH 2/2] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 test/test_cuda/test_multiple_card.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/test/test_cuda/test_multiple_card.py b/test/test_cuda/test_multiple_card.py
index 43e67e957..f2f1685be 100644
--- a/test/test_cuda/test_multiple_card.py
+++ b/test/test_cuda/test_multiple_card.py
@@ -241,7 +241,7 @@ def test_device_map_dict(self):
             device_map=device_map,
         )
         autoround.quantize()
-        
+
         # test rtn
         autoround = AutoRound(
             model_name,