[TRTLLM-6262] Fix Llama4 Scout FP4 crash issue (#5834)

Signed-off-by: Chenfei Zhang <[email protected]>

Author: chenfeiz0326

tensorrt_llm/_torch/models/modeling_llama.py

@@ -159,15 +159,19 @@ def _forward_nope(
             q = self._attention_scaling(q, position_ids)
 
         out_scale = None
+        out_scale_sf = None
         if self.o_proj.has_fp8_qdq or self.o_proj.has_nvfp4 or self.o_proj.has_fp8_block_scales:
             out_scale = self.o_proj.inv_input_scale
+        if self.o_proj.has_nvfp4 and self.support_nvfp4_output:
+            out_scale_sf = self.o_proj.input_scale
 
         q, k, v = self.convert_qkv(q, k, v)
         attn_output = self.attn.forward(q,
                                         k,
                                         v,
                                         attn_metadata,
                                         out_scale=out_scale,
+                                        out_scale_sf=out_scale_sf,
                                         attention_mask=attention_mask,
                                         mrope_config=mrope_config)