diff --git a/demo/nvflare/horizontal/README.md b/demo/nvflare/horizontal/README.md
index 19ac4cf4e..7337f1720 100644
--- a/demo/nvflare/horizontal/README.md
+++ b/demo/nvflare/horizontal/README.md
@@ -85,8 +85,8 @@ shutdown server
 ## Training with GPUs
 
 To demo with Federated Learning using GPUs, make sure your machine has at least 2 GPUs.
-Build XGBoost with the federated learning plugin enabled along with CUDA, but with NCCL
-turned off (see the [README](../../plugin/federated/README.md)).
+Build XGBoost with the federated learning plugin enabled along with CUDA
+(see the [README](../../plugin/federated/README.md)).
 
-Modify `config/config_fed_client.json` and set `use_gpus` to `true`, then repeat the steps
+Modify `../config/config_fed_client.json` and set `use_gpus` to `true`, then repeat the steps
 above.
diff --git a/demo/nvflare/horizontal/custom/trainer.py b/demo/nvflare/horizontal/custom/trainer.py
index b1ec94211..4f20b2f39 100644
--- a/demo/nvflare/horizontal/custom/trainer.py
+++ b/demo/nvflare/horizontal/custom/trainer.py
@@ -67,7 +67,7 @@ class XGBoostTrainer(Executor):
             dtest = xgb.DMatrix('agaricus.txt.test?format=libsvm')
 
             # Specify parameters via map, definition are same as c++ version
-            param = {'max_depth': 2, 'eta': 1, 'objective': 'binary:logistic'}
+            param = {'tree_method': 'hist', 'max_depth': 2, 'eta': 1, 'objective': 'binary:logistic'}
             if self._use_gpus:
                 self.log_info(fl_ctx, f'Training with GPU {rank}')
                 param['device'] = f"cuda:{rank}"
diff --git a/demo/nvflare/vertical/README.md b/demo/nvflare/vertical/README.md
index f9cca57d9..d63b2bca4 100644
--- a/demo/nvflare/vertical/README.md
+++ b/demo/nvflare/vertical/README.md
@@ -56,4 +56,9 @@ shutdown server
 
 ## Training with GPUs
 
-Currently GPUs are not yet supported by vertical federated XGBoost.
+To demo with Vertical Federated Learning using GPUs, make sure your machine has at least 2 GPUs.
+Build XGBoost with the federated learning plugin enabled along with CUDA
+(see the [README](../../plugin/federated/README.md)).
+
+Modify `../config/config_fed_client.json` and set `use_gpus` to `true`, then repeat the steps
+above.
diff --git a/demo/nvflare/vertical/custom/trainer.py b/demo/nvflare/vertical/custom/trainer.py
index 1c235a439..efe320734 100644
--- a/demo/nvflare/vertical/custom/trainer.py
+++ b/demo/nvflare/vertical/custom/trainer.py
@@ -77,13 +77,15 @@ class XGBoostTrainer(Executor):
                 'gamma': 1.0,
                 'max_depth': 8,
                 'min_child_weight': 100,
-                'tree_method': 'approx',
+                'tree_method': 'hist',
                 'grow_policy': 'depthwise',
                 'objective': 'binary:logistic',
                 'eval_metric': 'auc',
             }
             if self._use_gpus:
-                self.log_info(fl_ctx, 'GPUs are not currently supported by vertical federated XGBoost')
+                if self._use_gpus:
+                    self.log_info(fl_ctx, f'Training with GPU {rank}')
+                    param['device'] = f"cuda:{rank}"
 
             # specify validations set to watch performance
             watchlist = [(dtest, "eval"), (dtrain, "train")]