diff --git a/vllm/cutedsl_quant_method.py b/vllm/cutedsl_quant_method.py
index a858144e..6e032a0e 100644
--- a/vllm/cutedsl_quant_method.py
+++ b/vllm/cutedsl_quant_method.py
@@ -98,7 +98,11 @@ class CuTeDSLNvfp4Method(LinearMethodBase):
         layer._cutedsl_runner_id = register_runner(runner)
         layer._cutedsl_out_features = out_features
 
-        # Warmup: compute activation global scale from sample data
+        # Warmup: compute activation global scale from sample data.
+        # The checkpoint's input_scale is a calibration-time value that does NOT
+        # match what quantize_activation_nvfp4 expects at runtime. Using it
+        # produces garbage output (empty EOS tokens). The correct approach is
+        # a warmup forward pass that measures the actual activation distribution.
         with torch.no_grad():
             sample = torch.randn(min(8, 256), in_features,
                                  dtype=torch.bfloat16, device=device) * 2.0
diff --git a/vllm/kernels/linear/nvfp4/cutedsl.py b/vllm/kernels/linear/nvfp4/cutedsl.py
index 55f58b61..060a6f99 100644
--- a/vllm/kernels/linear/nvfp4/cutedsl.py
+++ b/vllm/kernels/linear/nvfp4/cutedsl.py
@@ -80,16 +80,17 @@ class CuTeDSLNvFp4LinearKernel(NvFp4LinearKernel):
         runner.gs = [gs]
         runner.finalize_weights()
 
-        activation_global_scale = 1.0 / 2688.0
-        if hasattr(layer, 'input_global_scale_inv') and layer.input_global_scale_inv is not None:
-            inv = layer.input_global_scale_inv.data.item()
-            if inv != 0:
-                # input_global_scale_inv = 1.0 / input_global_scale
-                # input_global_scale = 1.0 / nvfp4_global_scale (the dequant scale)
-                # So input_global_scale_inv = nvfp4_global_scale = amax / (6.0 * 448.0)
-                # This is exactly what quantize_activation_nvfp4 expects.
-                activation_global_scale = inv
-        runner._activation_global_scale = activation_global_scale
+        # Warmup: compute activation global scale from sample data.
+        # The checkpoint's input_scale is a calibration-time value that does NOT
+        # match what quantize_activation_nvfp4 expects at runtime. Using it
+        # produces garbage output (empty EOS tokens). The correct approach is
+        # a warmup forward pass that measures the actual activation distribution.
+        with torch.no_grad():
+            sample = torch.randn(
+                min(8, 256), in_features,
+                dtype=torch.bfloat16, device=str(device),
+            ) * 2.0
+            runner.compute_activation_global_scale(sample)
 
         # Register the runner and store the ID (not the runner itself)
         layer._cutedsl_runner_id = register_runner(runner)