[BugFix][Relax] Select target-specific pipeline in tvm.compile when GPU target is provided

python/tvm/relax/backend/cpu_generic/pipeline.py

@@ -22,7 +22,10 @@
 
 def library_dispatch_passes(target: tvm.target.Target):  # pylint: disable=unused-argument
     """The default library dispatch passes for CPU backend."""
-    return []
+    return [
+        relax.backend.DispatchSampling(),
+        relax.backend.DispatchSortScan(),
+    ]
 
 
 def legalize_passes(target: tvm.target.Target):  # pylint: disable=unused-argument

python/tvm/relax/vm_build.py

@@ -248,7 +248,21 @@ def _extract_attrs(mod: tvm.IRModule):
 
     if relax_pipeline is not None:
         if isinstance(relax_pipeline, str):
-            relax_pipeline = relax.get_pipeline(relax_pipeline)
+            # For GPU targets, prefer the target-specific pipeline which
+            # includes DLight scheduling. Without it, TIR functions generated
+            # from ops like Clip/ReLU6 lack thread bindings and fail
+            # VerifyMemory. CPU targets continue to use the generic pipeline
+            # since the CPU-specific pipeline applies fusion passes that can
+            # incorrectly remove call_pure_packed calls whose results are
+            # unused but whose side effects are relied upon.
+            _is_gpu = target is not None and "gpu" in target.keys
+            if relax_pipeline == "default" and _is_gpu:
+                try:
+                    relax_pipeline = relax.get_default_pipeline(target)
+                except (ValueError, AttributeError):
+                    relax_pipeline = relax.get_pipeline(relax_pipeline)
+            else:
+                relax_pipeline = relax.get_pipeline(relax_pipeline)
         if target is None:
             mod = relax_pipeline(mod)
         else: