diff --git a/README.md b/README.md
index 607cffb9e74..51630be811f 100644
--- a/README.md
+++ b/README.md
@@ -199,7 +199,7 @@ It is recommended to use [NGC PyTorch Container](https://catalog.ngc.nvidia.com/
 
 > [!Note]
 > Ensure that you select a PyTorch container image version that matches the version of TensorRT-LLM you are using.
-> For example, if you are using `tensorrt-llm==1.1.0rc3`, use the PyTorch container image version `25.06`.
+> For example, if you are using `tensorrt-llm==1.1.0rc5`, use the PyTorch container image version `25.06`.
 > To find the correct PyTorch container version for your desired `tensorrt-llm` release, visit the [TensorRT-LLM Dockerfile.multi](https://github.com/NVIDIA/TensorRT-LLM/blob/main/docker/Dockerfile.multi) on GitHub. Switch to the branch that matches your `tensorrt-llm` version, and look for the `BASE_TAG` line to identify the recommended PyTorch container tag.
 
 > [!Important]
diff --git a/container/build.sh b/container/build.sh
index a095db4c9aa..cee547193c6 100755
--- a/container/build.sh
+++ b/container/build.sh
@@ -89,7 +89,7 @@ TENSORRTLLM_PIP_WHEEL_DIR="/tmp/trtllm_wheel/"
 # TensorRT-LLM commit to use for building the trtllm wheel if not provided.
 # Important Note: This commit is not used in our CI pipeline. See the CI
 # variables to learn how to run a pipeline with a specific commit.
-DEFAULT_EXPERIMENTAL_TRTLLM_COMMIT="e81c50dbd2811ec858eccc2c71b5e7a330ff7e24"
+DEFAULT_EXPERIMENTAL_TRTLLM_COMMIT="0c9430e5a530ba958fc9dca561a3ad865ad9f492"
 TRTLLM_COMMIT=""
 TRTLLM_USE_NIXL_KVCACHE_EXPERIMENTAL="0"
 TRTLLM_GIT_URL=""
@@ -98,7 +98,7 @@ TRTLLM_GIT_URL=""
 TENSORRTLLM_INDEX_URL="https://pypi.python.org/simple"
 # TODO: Remove the version specification from here and use the ai-dynamo[trtllm] package.
 # Need to update the Dockerfile.trtllm to use the ai-dynamo[trtllm] package.
-DEFAULT_TENSORRTLLM_PIP_WHEEL="tensorrt-llm==1.1.0rc3"
+DEFAULT_TENSORRTLLM_PIP_WHEEL="tensorrt-llm==1.1.0rc5"
 TENSORRTLLM_PIP_WHEEL=""
 
 
diff --git a/docs/guides/run_kvbm_in_trtllm.md b/docs/guides/run_kvbm_in_trtllm.md
index 760dfa71380..d5d846c9054 100644
--- a/docs/guides/run_kvbm_in_trtllm.md
+++ b/docs/guides/run_kvbm_in_trtllm.md
@@ -27,7 +27,7 @@ To learn what KVBM is, please check [here](https://docs.nvidia.com/dynamo/latest
 > - KVBM only supports TensorRT-LLM’s PyTorch backend.
 > - To enable disk cache offloading, you must first enable a CPU memory cache offloading.
 > - Disable partial reuse `enable_partial_reuse: false` in the LLM API config’s `kv_connector_config` to increase offloading cache hits.
-> - KVBM requires TensorRT-LLM at commit ce580ce4f52af3ad0043a800b3f9469e1f1109f6 or newer.
+> - KVBM requires TensorRT-LLM v1.1.0rc5 or newer.
 > - Enabling KVBM metrics with TensorRT-LLM is still a work in progress.
 
 ## Quick Start
@@ -38,12 +38,8 @@ To use KVBM in TensorRT-LLM, you can follow the steps below:
 # start up etcd for KVBM leader/worker registration and discovery
 docker compose -f deploy/docker-compose.yml up -d
 
-# Build a container that includes TensorRT-LLM and KVBM. Note: KVBM integration is only available in TensorRT-LLM commit dcd110cfac07e577ce01343c455917832b0f3d5e or newer.
-# When building with the --tensorrtllm-commit option, you may notice that https://github.com keeps prompting for a username and password.
-# This happens because cloning TensorRT-LLM can hit GitHub’s rate limit.
-# To work around this, you can keep pressing "Enter" or "Return.".
-# Setting "export GIT_LFS_SKIP_SMUDGE=1" may also reduce the number of prompts.
-./container/build.sh --framework trtllm --tensorrtllm-commit dcd110cfac07e577ce01343c455917832b0f3d5e --enable-kvbm
+# Build a container that includes TensorRT-LLM and KVBM.
+./container/build.sh --framework trtllm --enable-kvbm
 
 # launch the container
 ./container/run.sh --framework trtllm -it --mount-workspace --use-nixl-gds
diff --git a/docs/support_matrix.md b/docs/support_matrix.md
index c6dc81858ef..7fcca6bf5bd 100644
--- a/docs/support_matrix.md
+++ b/docs/support_matrix.md
@@ -67,7 +67,7 @@ If you are using a **GPU**, the following GPU models and architectures are suppo
 | **Build Dependency** | **Version**                                                                      |
 | :------------------- | :------------------------------------------------------------------------------- |
 | **Base Container**   | [25.03](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/cuda-dl-base/tags) |
-| **TensorRT-LLM**     | 1.1.0rc3                                                                         |
+| **TensorRT-LLM**     | 1.1.0rc5                                                                         |
 | **NIXL**             | 0.4.1                                                                            |
 | **vLLM**             | 0.10.1.1                                                                         |
 | **SGLang**           | 0.5.0rc2                                                                         |
diff --git a/lib/bindings/python/Cargo.lock b/lib/bindings/python/Cargo.lock
index a2ab9a108fd..ba935069d41 100644
--- a/lib/bindings/python/Cargo.lock
+++ b/lib/bindings/python/Cargo.lock
@@ -1469,6 +1469,7 @@ dependencies = [
  "rustpython-parser",
  "serde",
  "serde_json",
+ "tokio",
  "tracing",
  "uuid",
 ]
diff --git a/pyproject.toml b/pyproject.toml
index 90a89aa8d2f..eff8b4f4264 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -48,7 +48,7 @@ Repository = "https://github.com/ai-dynamo/dynamo.git"
 [project.optional-dependencies]
 trtllm =[
     "uvloop",
-    "tensorrt-llm==1.1.0rc3",
+    "tensorrt-llm==1.1.0rc5",
 ]
 
 vllm = [