diff --git a/fern/docs/pages/installation/installation.mdx b/fern/docs/pages/installation/installation.mdx
index b41c1e6..26fc201 100644
--- a/fern/docs/pages/installation/installation.mdx
+++ b/fern/docs/pages/installation/installation.mdx
@@ -137,6 +137,8 @@ Follow these steps to set up a local TensorRT-powered PrivateGPT:
 
 - Nvidia Cuda 12.2 or higher is currently required to run TensorRT-LLM.
 
+- Install tensorrt_llm via pip with pip install --no-cache-dir --extra-index-url https://pypi.nvidia.com tensorrt-llm as explained [here](https://pypi.org/project/tensorrt-llm/)
+
 - For this example we will use Llama2. The Llama2 model files need to be created via scripts following the instructions [here](https://github.com/NVIDIA/trt-llm-rag-windows/blob/release/1.0/README.md#building-trt-engine).
 The following files will be created from following the steps in the link:
 
diff --git a/poetry.lock b/poetry.lock
index dbe2822..ebe0ffb 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -4906,16 +4906,6 @@ files = [
 [package.extras]
 doc = ["reno", "sphinx", "tornado (>=4.5)"]
 
-[[package]]
-name = "tensorrt-llm"
-version = "0.8.0"
-description = "A fake package to warn the user they are not installing the correct package."
-optional = true
-python-versions = ">=3.7, <4"
-files = [
-    {file = "tensorrt-llm-0.8.0.tar.gz", hash = "sha256:8bd59bf59766bb16f81bd330ca38765a532a21a35d323fd33929c80a6ec53eaf"},
-]
-
 [[package]]
 name = "tiktoken"
 version = "0.5.2"
@@ -5971,7 +5961,7 @@ embeddings-huggingface = ["llama-index-embeddings-huggingface"]
 embeddings-openai = ["llama-index-embeddings-openai"]
 embeddings-sagemaker = ["boto3"]
 llms-llama-cpp = ["llama-index-llms-llama-cpp"]
-llms-nvidia-tensorrt = ["llama-index-llms-nvidia-tensorrt", "tensorrt_llm"]
+llms-nvidia-tensorrt = ["llama-index-llms-nvidia-tensorrt"]
 llms-ollama = ["llama-index-llms-ollama"]
 llms-openai = ["llama-index-llms-openai"]
 llms-openai-like = ["llama-index-llms-openai-like"]
@@ -5984,4 +5974,4 @@ vector-stores-qdrant = ["llama-index-vector-stores-qdrant"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<3.12"
-content-hash = "da01e96bb8eb18aa3b6608cf60384771ad674b6ec7a26a685a62274c0302c8f9"
+content-hash = "39f0ac666402807cde29f763c14dfb6b2fc9862c0cd31de398c67a1fedbb4b12"
diff --git a/pyproject.toml b/pyproject.toml
index 5db0d63..82c8775 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -29,8 +29,6 @@ llama-index-vector-stores-postgres = {version ="^0.1.2", optional = true}
 llama-index-llms-nvidia-tensorrt = {version ="^0.1.2", optional = true}
 # Optional Sagemaker dependency
 boto3 = {version ="^1.34.51", optional = true}
-# Optional Nvidia TensorRT dependency
-tensorrt_llm = {version ="^0.8.0", optional = true}
 # Optional UI
 gradio = {version ="^4.19.2", optional = true}
 
@@ -41,7 +39,7 @@ llms-openai = ["llama-index-llms-openai"]
 llms-openai-like = ["llama-index-llms-openai-like"]
 llms-ollama = ["llama-index-llms-ollama"]
 llms-sagemaker = ["boto3"]
-llms-nvidia-tensorrt = ["tensorrt_llm", "llama-index-llms-nvidia-tensorrt"]
+llms-nvidia-tensorrt = ["llama-index-llms-nvidia-tensorrt"]
 embeddings-huggingface = ["llama-index-embeddings-huggingface"]
 embeddings-openai = ["llama-index-embeddings-openai"]
 embeddings-sagemaker = ["boto3"]