Upgrade tensorrt_llm to v0.18.2

Signed-off-by: makaveli10 <vineet.suryan@collabora.com>

docker/Dockerfile.tensorrt

@@ -1,19 +1,19 @@
-FROM nvidia/cuda:12.4.1-base-ubuntu22.04 AS base
+FROM nvidia/cuda:12.8.1-base-ubuntu22.04 AS base
 
 ARG DEBIAN_FRONTEND=noninteractive
 
 RUN apt-get update && apt-get install -y \
     python3.10 python3-pip openmpi-bin libopenmpi-dev git git-lfs wget \
+    && apt install python-is-python3 \
+    && pip install --upgrade pip setuptools \
     && rm -rf /var/lib/apt/lists/*
 
 FROM base AS devel
-RUN pip3 install --no-cache-dir -U tensorrt_llm==0.15.0.dev2024111200 --extra-index-url https://pypi.nvidia.com
+RUN pip install --no-cache-dir -U tensorrt_llm==0.18.2 --extra-index-url https://pypi.nvidia.com
 WORKDIR /app
-RUN git clone https://github.com/NVIDIA/TensorRT-LLM.git && cd TensorRT-LLM && \
-    git checkout c629546ce429623c8a163633095230154a6f0574 && cd ../ && \
-    mv TensorRT-LLM/examples ./TensorRT-LLM-examples && \
-    rm -rf TensorRT-LLM
-
+RUN git clone -b v0.18.2 https://github.com/NVIDIA/TensorRT-LLM.git \
+    && mv TensorRT-LLM/examples ./TensorRT-LLM-examples \
+    && rm -rf TensorRT-LLM
 
 FROM devel AS release
 WORKDIR /app
@@ -25,7 +25,6 @@ RUN apt update && bash setup.sh && rm setup.sh
 
 COPY requirements/server.txt .
 RUN pip install --no-cache-dir -r server.txt && rm server.txt
-RUN pip install pynvml==11.5.0
 COPY whisper_live ./whisper_live
 COPY scripts/build_whisper_tensorrt.sh .
 COPY run_server.py .