diff --git a/python/sglang/srt/server_args.py b/python/sglang/srt/server_args.py
index 2c8525f71..c000a88eb 100644
--- a/python/sglang/srt/server_args.py
+++ b/python/sglang/srt/server_args.py
@@ -5805,20 +5805,6 @@ class ServerArgs:
                 "Page first layout is not supported with direct IO backend, switching to page first direct layout"
             )
 
-        # The page_first kernel write-back relies on the CUDA-only JIT staged
-        # kernel. On ROCm it falls back to a kernel that requires CUDA index
-        # tensors and crashes on host write-back, so use layer_first there.
-        if (
-            self.hicache_mem_layout == "page_first"
-            and self.hicache_io_backend == "kernel"
-            and is_hip()
-        ):
-            self.hicache_mem_layout = "layer_first"
-            logger.warning(
-                "page_first kernel write-back requires the CUDA JIT kernel; "
-                "falling back to layer_first layout on ROCm."
-            )
-
     def _resolve_storage_layout_compatibility(self):
         if (
             self.hicache_storage_backend != "mooncake"