diff --git a/python/sglang/srt/layers/attention/aiter_backend.py b/python/sglang/srt/layers/attention/aiter_backend.py
index d851040cfc37..dcdd0328ca8c 100644
--- a/python/sglang/srt/layers/attention/aiter_backend.py
+++ b/python/sglang/srt/layers/attention/aiter_backend.py
@@ -123,7 +123,17 @@ def __init__(
             model_runner.model_config.num_attention_heads // get_attention_tp_size()
         )
         self.head_dim = model_runner.model_config.head_dim
-        self.v_head_dim = model_runner.token_to_kv_pool.get_value_buffer(0).shape[-1]
+        # self.v_head_dim = model_runner.token_to_kv_pool.get_value_buffer(0).shape[-1]
+        if (
+            model_runner.hybrid_gdn_config is not None
+            or model_runner.kimi_linear_config is not None
+        ):
+            # For hybrid linear models, layer_id = 0 may not be full attention
+            self.v_head_dim = model_runner.token_to_kv_pool.get_v_head_dim()
+        else:
+            self.v_head_dim = model_runner.token_to_kv_pool.get_value_buffer(0).shape[
+                -1
+            ]
         self.num_kv_head = model_runner.model_config.get_num_kv_heads(
             get_attention_tp_size()
         )
diff --git a/python/sglang/srt/layers/attention/attention_registry.py b/python/sglang/srt/layers/attention/attention_registry.py
index 25ffc3f0b412..e3177ae261e5 100644
--- a/python/sglang/srt/layers/attention/attention_registry.py
+++ b/python/sglang/srt/layers/attention/attention_registry.py
@@ -1,5 +1,6 @@
 import logging
 from typing import TYPE_CHECKING
+from sglang.srt.utils import get_bool_env_var
 
 logger = logging.getLogger(__name__)
 
@@ -221,6 +222,14 @@ def attn_backend_wrapper(runner: "ModelRunner", full_attn_backend: "AttentionBac
                 "Expected hybrid GDN or NemotronH models, but got unknown model."
             )
         full_attn_layers = cfg.full_attention_layer_ids
+        if get_bool_env_var("SGLANG_USE_AITER_PA"):
+            from sglang.srt.layers.attention.aiter_backend import AiterAttnBackend
+            return HybridLinearAttnBackend(
+                full_attn_backend,
+                linear_attn_backend,
+                full_attn_layers,
+                AiterAttnBackend(runner),
+            )
         return HybridLinearAttnBackend(
             full_attn_backend, linear_attn_backend, full_attn_layers
         )
diff --git a/python/sglang/srt/layers/attention/hybrid_linear_attn_backend.py b/python/sglang/srt/layers/attention/hybrid_linear_attn_backend.py
index 47a74066cd0d..a405b1df959f 100644
--- a/python/sglang/srt/layers/attention/hybrid_linear_attn_backend.py
+++ b/python/sglang/srt/layers/attention/hybrid_linear_attn_backend.py
@@ -1567,11 +1567,16 @@ def __init__(
         full_attn_backend: AttentionBackend,
         linear_attn_backend: MambaAttnBackendBase,
         full_attn_layers: list[int],
+        full_attn_decode_backend: Optional[AttentionBackend] = None,
     ):
         self.full_attn_layers = full_attn_layers
         self.full_attn_backend = full_attn_backend
         self.linear_attn_backend = linear_attn_backend
         self.attn_backend_list = [full_attn_backend, linear_attn_backend]
+        self.full_attn_decode_backend = None
+        if full_attn_decode_backend is not None:
+            self.full_attn_decode_backend = full_attn_decode_backend
+            self.attn_backend_list += [full_attn_decode_backend]
 
     def init_forward_metadata(self, forward_batch: ForwardBatch):
         for attn_backend in self.attn_backend_list:
@@ -1643,9 +1648,14 @@ def forward_decode(
     ):
         layer_id = layer.layer_id if layer else kwargs["layer_id"]
         if layer_id in self.full_attn_layers:
-            return self.full_attn_backend.forward_decode(
-                q, k, v, layer, forward_batch, save_kv_cache, **kwargs
-            )
+            if self.full_attn_decode_backend is not None:
+                return self.full_attn_decode_backend.forward_decode(
+                    q, k, v, layer, forward_batch, save_kv_cache, **kwargs
+                )
+            else:
+                return self.full_attn_backend.forward_decode(
+                    q, k, v, layer, forward_batch, save_kv_cache, **kwargs
+                )
         # Linear attention backend
         return self.linear_attn_backend.forward_decode(
             q=q,