diff --git a/deepinfer/model_executor/models/v4_modules/attn.py b/deepinfer/model_executor/models/v4_modules/attn.py
index c14f88d..326a0d9 100644
--- a/deepinfer/model_executor/models/v4_modules/attn.py
+++ b/deepinfer/model_executor/models/v4_modules/attn.py
@@ -200,6 +200,23 @@ class V4AttentionBase(nn.Module):
     def _wv_and_o_proj(self, context: torch.Tensor | tuple[torch.Tensor, torch.Tensor], positions: torch.Tensor) -> torch.Tensor:
         if not self.use_fused_norm_rope_attn_rope_cast:
             self.rotary_emb(positions, context[..., -self.qk_rope_head_dim :], conjugate=True)
+        if (
+            PLATFORM.is_neuron
+            and not isinstance(context, tuple)
+            and not self.use_fp8_einsum_output
+            and self.einsum_out_clamp_value is None
+            and nki_gemm.has_kernel(self.wv_weight)
+        ):
+            # The NKI kernel quantizes the bf16 context itself (1x32, as per_token_cast): no fp8 encode in the graph.
+            ctx = context.view(context.shape[0], self.n_wv_group, self.wv_group_dim)
+            wv = torch.stack([nki_gemm.linear_qdq(ctx[:, h], self.wv_weight, group=h) for h in range(self.n_wv_group)], dim=1)
+            out = self.out_proj(wv.flatten(1, 2))
+            tp_group = getattr(self, "tp_group", None)
+            if tp_group is not None:
+                import torch.distributed._functional_collectives as funcol
+
+                out = funcol.wait_tensor(funcol.all_reduce(out.float(), "sum", tp_group)).to(out.dtype)
+            return out
         if isinstance(context, tuple):
             context_fp8, context_sf = context
             gran = 32