diff --git a/components/backends/trtllm/engine_configs/llama4/eagle_one_model/eagle_agg.yml b/components/backends/trtllm/engine_configs/llama4/eagle_one_model/eagle_agg.yml
new file mode 100644
index 0000000000..56ccf8d07d
--- /dev/null
+++ b/components/backends/trtllm/engine_configs/llama4/eagle_one_model/eagle_agg.yml
@@ -0,0 +1,38 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+backend: pytorch
+tensor_parallel_size: 8
+moe_expert_parallel_size: 8
+max_batch_size: 8
+max_num_tokens: 4096
+disable_overlap_scheduler: true # disable_overlap_scheduler is having acc issue on both aggregated and disaggregated serving
+
+# Enable Speculative Decoding in the model engine
+speculative_config:
+  decoding_type: Eagle
+  max_draft_len: 3
+  pytorch_weights_path: nvidia/Llama-4-Maverick-17B-128E-Eagle3
+  eagle3_one_model: true
+
+kv_cache_config:
+  free_gpu_memory_fraction: 0.5
+  enable_block_reuse: false # true when target and draft are same kv dtype
+
+cuda_graph_config:
+  padding_enabled: true
+  max_batch_size: 8
+
+print_iter_log: true
diff --git a/components/backends/trtllm/engine_configs/llama4/eagle_one_model/eagle_decode.yaml b/components/backends/trtllm/engine_configs/llama4/eagle_one_model/eagle_decode.yaml
new file mode 100644
index 0000000000..556a1365f5
--- /dev/null
+++ b/components/backends/trtllm/engine_configs/llama4/eagle_one_model/eagle_decode.yaml
@@ -0,0 +1,40 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+backend: pytorch
+tensor_parallel_size: 8
+moe_expert_parallel_size: 8
+max_batch_size: 256
+max_num_tokens: 1024
+# 8704 = 8192 ISL + 512 OSL
+max_seq_len: 8704
+disable_overlap_scheduler: true
+
+# Enable Speculative Decoding in the model engine
+speculative_config:
+  decoding_type: Eagle
+  max_draft_len: 3
+  pytorch_weights_path: nvidia/Llama-4-Maverick-17B-128E-Eagle3
+  eagle3_one_model: True
+
+kv_cache_config:
+  free_gpu_memory_fraction: 0.5
+  enable_block_reuse: false
+
+cuda_graph_config:
+  padding_enabled: true
+  max_batch_size: 256
+
+print_iter_log: true
diff --git a/components/backends/trtllm/engine_configs/llama4/eagle_one_model/eagle_prefill.yaml b/components/backends/trtllm/engine_configs/llama4/eagle_one_model/eagle_prefill.yaml
new file mode 100644
index 0000000000..a75d2a6219
--- /dev/null
+++ b/components/backends/trtllm/engine_configs/llama4/eagle_one_model/eagle_prefill.yaml
@@ -0,0 +1,34 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+backend: pytorch
+tensor_parallel_size: 8
+moe_expert_parallel_size: 8
+max_batch_size: 1
+max_num_tokens: 8192
+max_seq_len: 8192
+print_iter_log: true
+disable_overlap_scheduler: true
+
+# Enable Speculative Decoding in the model engine
+speculative_config:
+  decoding_type: Eagle
+  max_draft_len: 3
+  pytorch_weights_path: nvidia/Llama-4-Maverick-17B-128E-Eagle3
+  eagle3_one_model: True
+
+kv_cache_config:
+  free_gpu_memory_fraction: 0.5
+  enable_block_reuse: false
diff --git a/components/backends/trtllm/llama4_plus_eagle.md b/components/backends/trtllm/llama4_plus_eagle.md
index 92d9704997..2d542f7a1a 100644
--- a/components/backends/trtllm/llama4_plus_eagle.md
+++ b/components/backends/trtllm/llama4_plus_eagle.md
@@ -34,6 +34,12 @@ For advanced control over how requests are routed between prefill and decode wor
   * Built with a version of TensorRT-LLM based on the 0.21 release [Link](https://github.com/NVIDIA/TensorRT-LLM/tree/release/0.21)
 * If you need to download model weights off huggingface, make sure you run the command `huggingface-cli login` and have access to the necessary gated models.
 
+## Eagle3-one-model
+* Eagle3-one-model (`eagle3_one_model=True`) config is added in `engine_configs/llama4/eagle_one_model`. Build dynamo with the latest commit `66f299a` in TRTLLM 1.0.0.rc2 [Link](https://github.com/NVIDIA/TensorRT-LLM/commits/v1.0.0rc2/).
+* The configs in `engine_configs/llama4/eagle_one_model` are tested with 8xH100 cluster. Be sure to change the `NUM_GPUS_PER_NODE` accordingly or change TP/EP size in config. 1 8xH100 node for aggregated .yml file, 2 8xH100 for prefill/decode .yml file.
+* The current `./multinode/start_frontend_services.sh` may got ran `NUM_GPUS_PER_NODE` times depending on how srun/mpi is launched, beware that the frontend service only needs to be ran once.
+* Eagle3-one-model appends the eagle3 layer at the end of the TRTLLM engine, instead of sending base/draft requests between 2 engines. Visit TRTLLM for more information.
+
 
 ## Setup
 
@@ -77,3 +83,17 @@ export DECODE_ENGINE_CONFIG="/mnt/engine_configs/llama4/eagle/eagle_decode.yaml"
 ## Example Request
 
 See [here](./multinode/multinode-examples.md#example-request) to learn how to send a request to the deployment.
+
+```
+curl localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d '{
+        "model": "nvidia/Llama-4-Maverick-17B-128E-Instruct-FP8",
+        "messages": [{"role": "user", "content": "Why is NVIDIA a great company?"}],
+        "max_tokens": 1024
+    }' -w "\n"
+
+
+# output:
+{"id":"cmpl-3e87ea5c-010e-4dd2-bcc4-3298ebd845a8","choices":[{"text":"NVIDIA is considered a great company for several reasons:\n\n1. **Technological Innovation**: NVIDIA is a leader in the field of graphics processing units (GPUs) and has been at the forefront of technological innovation.
+...
+and the broader tech industry.\n\nThese factors combined have contributed to NVIDIA's status as a great company in the technology sector.","index":0,"logprobs":null,"finish_reason":"stop"}],"created":1753329671,"model":"nvidia/Llama-4-Maverick-17B-128E-Instruct-FP8","system_fingerprint":null,"object":"text_completion","usage":{"prompt_tokens":16,"completion_tokens":562,"total_tokens":578,"prompt_tokens_details":null,"completion_tokens_details":null}}
+```