diff --git a/vllm/patches/deepseek_v4.py b/vllm/patches/deepseek_v4.py
index 94c183db..9b2b9ce1 100644
--- a/vllm/patches/deepseek_v4.py
+++ b/vllm/patches/deepseek_v4.py
@@ -1534,6 +1534,27 @@ class DeepseekV4Model(nn.Module):
                             loaded_params.add(is_name)
                         continue
                     
+                    # Handle uint8 NVFP4 packed → bf16 unpack for non-stacked
+                    # params (e.g. indexer.weights_proj). Checkpoint stores
+                    # NVFP4 as uint8 (2 values/byte), but model param is bf16.
+                    if (loaded_weight.dtype == torch.uint8
+                            and param.data.dtype != torch.uint8
+                            and loaded_weight.shape[-1] * 2 == param.data.shape[-1]):
+                        FP4_LUT = torch.tensor([
+                            0.0, 0.5, 1.0, 1.5, 2.0, 3.0, 4.0, 6.0,
+                            -0.0, -0.5, -1.0, -1.5, -2.0, -3.0, -4.0, -6.0,
+                        ], dtype=torch.float32, device=loaded_weight.device)
+                        lower = FP4_LUT[(loaded_weight & 0x0F).long()]
+                        upper = FP4_LUT[((loaded_weight >> 4) & 0x0F).long()]
+                        out = torch.empty(
+                            *loaded_weight.shape[:-1],
+                            loaded_weight.shape[-1] * 2,
+                            dtype=torch.float32, device=loaded_weight.device,
+                        )
+                        out[..., 0::2] = lower
+                        out[..., 1::2] = upper
+                        loaded_weight = out.to(torch.bfloat16)
+
                     weight_loader = getattr(
                         param, "weight_loader", default_weight_loader
                     )