diff --git a/infra/aws_neuron/Dockerfile.base b/infra/aws_neuron/Dockerfile.base
deleted file mode 100644
index b7fd4f61..00000000
--- a/infra/aws_neuron/Dockerfile.base
+++ /dev/null
@@ -1,76 +0,0 @@
-# Adapted from: https://github.com/huggingface/optimum-neuron/blob/main/text-generation-inference/Dockerfile
-# Python base image
-FROM ubuntu:22.04 AS base
-
-RUN apt-get update -y \
- && apt-get install -y --no-install-recommends \
-    python3-pip \
-    python3-setuptools \
-    python-is-python3 \
-    && rm -rf /var/lib/apt/lists/* \
-    && apt-get clean
-RUN pip3 --no-cache-dir install --upgrade pip
-
-# Neuron base image (used for deployment)
-FROM base AS neuron
-# Install system prerequisites
-RUN  apt-get update -y \
- && apt-get install -y --no-install-recommends \
-    gnupg2 \
-    wget \
-    python3-dev \
-    && rm -rf /var/lib/apt/lists/* \
-    && apt-get clean
-
-RUN echo "deb https://apt.repos.neuron.amazonaws.com jammy main" > /etc/apt/sources.list.d/neuron.list
-RUN wget -qO - https://apt.repos.neuron.amazonaws.com/GPG-PUB-KEY-AMAZON-AWS-NEURON.PUB | apt-key add -
-
-# Install neuronx packages
-RUN apt-get update -y \
- && apt-get install -y --no-install-recommends \
-    aws-neuronx-dkms=2.18.20.0 \
-    aws-neuronx-collectives=2.22.33.0-d2128d1aa \
-    aws-neuronx-runtime-lib=2.22.19.0-5856c0b42 \
-    aws-neuronx-tools=2.19.0.0 \
-    libxml2 \
-    && rm -rf /var/lib/apt/lists/* \
-    && apt-get clean
-
-
-ENV PATH="/opt/bin/:/opt/aws/neuron/bin:${PATH}"
-
-FROM neuron AS infinity
-RUN apt-get update -y && apt-get install -y nano 
-WORKDIR /app
-
-COPY requirements_no_gpu.txt requirements_no_gpu.txt
-
-# RUN pip3 install \
-#     neuronx-cc==2.15.143.0 \
-#     torch-neuronx==2.1.2.2.3.2 \
-#     transformers-neuronx==0.12.313 \
-#     libneuronxla==2.0.5347.0 \
-#     --extra-index-url=https://pip.repos.neuron.amazonaws.com
-RUN pip3 config set global.extra-index-url https://pip.repos.neuron.amazonaws.com
-RUN pip3 install -r requirements_no_gpu.txt
-RUN pip3 install --upgrade-strategy eager optimum[neuronx]
-RUN pip3 install --upgrade \
-    neuronx-cc==2.* \
-    libneuronxla==2.0.5347.0 \
-    torch-neuronx==2.1.2.2.2.0 \
-    transformers-neuronx==0.12.313 \
-    torch==2.1.2.* \
-    torchvision==0.16.* \
-    neuronx_distributed \
-    --extra-index-url=https://pip.repos.neuron.amazonaws.com
-
-
-# COPY reqs_frozen.txt reqs_frozen.txt
-# RUN pip3 install -r reqs_frozen.txt 
-# Install optimum-neuron
-#14 19.70 Successfully installed aiohappyeyeballs-2.4.4 aiohttp-3.11.9 aiosignal-1.3.1 async-timeout-5.0.1 attrs-24.2.0 coloredlogs-15.0.1 datasets-3.1.0 dill-0.3.8 frozenlist-1.5.0 fsspec-2024.9.0 humanfriendly-10.0 multidict-6.1.0 multiprocess-0.70.16 optimum-1.18.0 optimum-neuron-0.0.1 pandas-2.2.3 propcache-0.2.1 pyarrow-18.1.0 pytz-2024.2 requests-2.32.3 sentencepiece-0.2.0 tokenizers-0.15.2 transformers-4.39.3 tzdata-2024.2 xxhash-3.5.0 yarl-1.18.3
-# RUN pip3 install optimum[neuronx] --extra-index-url=https://pip.repos.neuron.amazonaws.com
-# 
-# TGI base env
-ENV HF_HUB_ENABLE_HF_TRANSFER=1
-
diff --git a/infra/aws_neuron/Dockerfile.neuron b/infra/aws_neuron/Dockerfile.neuron
index e28ad1ff..d9bc8558 100644
--- a/infra/aws_neuron/Dockerfile.neuron
+++ b/infra/aws_neuron/Dockerfile.neuron
@@ -10,8 +10,6 @@ RUN pip config set global.extra-index-url https://pip.repos.neuron.amazonaws.com
 # req
 # RUN pip3 install --no-deps --upgrade optimum[neuronx]==1.20.0 
 RUN pip3 install --no-deps sentence_transformers==3.3.1 
-RUN apt-get update && apt-get install nano
-# RUN pip3 install --upgrade neuronx-cc==2.15.* torch-neuronx torchvision transformers-neuronx libneuronxla protobuf 
 # libneuronxla-2.0.5347.0 ml-dtypes-0.2.0 neuronx-cc-2.15.143.0+e39249ad setuptools-69.5.1 torch-neuronx-2.1.2.2.3.2 torch-xla-2.1.5 transformers-neuronx-0.12.313
 RUN pip3 install --upgrade neuronx-cc==2.15.* torch-neuronx torchvision transformers-neuronx libneuronxla protobuf optimum-neuron==0.0.20
 
diff --git a/infra/aws_neuron/reqs_frozen.txt b/infra/aws_neuron/reqs_frozen.txt
deleted file mode 100644
index 5bed363d..00000000
--- a/infra/aws_neuron/reqs_frozen.txt
+++ /dev/null
@@ -1,287 +0,0 @@
-# exported from neuron
---extra-index-url https://pypi.org/simple
---extra-index-url https://pip.repos.neuron.amazonaws.com
-absl-py
-accelerate==0.29.2
-aiohappyeyeballs==2.4.3
-aiohttp==3.10.10
-aiosignal==1.3.1
-amqp==5.2.0
-annotated-types==0.7.0
-ansicolors==1.1.8
-anyio==4.6.2.post1
-argon2-cffi==23.1.0
-argon2-cffi-bindings==21.2.0
-arrow==1.3.0
-astroid==3.2.4
-asttokens==2.4.1
-async-lru==2.0.4
-async-timeout==4.0.3
-attrs==24.2.0
-Automat==24.8.1
-awscli==1.34.19
-babel==2.16.0
-backoff==2.2.1
-beautifulsoup4==4.12.3
-billiard==4.2.0
-bleach==6.1.0
-boto3==1.35.19
-botocore==1.35.19
-build==1.2.2
-cachetools==5.5.0
-celery==5.4.0
-certifi==2024.8.30
-cffi==1.17.1
-charset-normalizer==3.4.0
-click==8.1.7
-click-didyoumean==0.3.1
-click-plugins==1.1.1
-click-repl==0.3.0
-cloud-tpu-client==0.10
-cloudpickle==3.0.0
-cmake==3.30.3
-colorama==0.4.6
-coloredlogs==15.0.1
-comm==0.2.2
-constantly==23.10.4
-contourpy==1.3.0
-cryptography==43.0.1
-cssselect==1.2.0
-cycler==0.12.1
-datasets==2.19.1
-debugpy==1.8.5
-decorator==5.1.1
-defusedxml==0.7.1
-diffusers==0.30.3
-dill==0.3.7
-diskcache==5.6.3
-distlib==0.3.8
-docutils==0.16
-dparse==0.6.3
-ec2-metadata==2.13.0
-einops==0.8.0
-entrypoints==0.4
-environment-kernels==1.2.0
-evaluate==0.4.1
-exceptiongroup==1.2.2
-executing==2.1.0
-fastapi==0.115.2
-fastjsonschema==2.20.0
-filelock==3.16.1
-flatbuffers==24.3.25
-fonttools==4.53.1
-fqdn==1.5.1
-frozenlist==1.4.1
-fsspec
-grpcio==1.67.1
-h11==0.14.0
-hf_transfer==0.1.8
-httpcore==1.0.5
-httpie==3.2.3
-httplib2==0.22.0
-httptools==0.6.4
-httpx==0.27.2
-huggingface-hub==0.26.0
-humanfriendly==10.0
-hyperlink==21.0.0
-idna==3.10
-imageio==2.35.1
-importlib_metadata==8.5.0
-incremental==24.7.2
-infinity_emb==0.0.70
-iniconfig==2.0.0
-ipykernel==6.29.5
-ipython==8.27.0
-ipywidgets==8.1.5
-islpy==2023.2.5
-isoduration==20.11.0
-isort==5.13.2
-itemadapter==0.9.0
-itemloaders==1.3.1
-jedi==0.19.1
-Jinja2==3.1.4
-jmespath==1.0.1
-joblib==1.4.2
-json5==0.9.25
-jsonpointer==3.0.0
-jsonschema==4.23.0
-jsonschema-specifications==2023.12.1
-kiwisolver==1.4.7
-kombu==5.4.1
-llvmlite==0.43.0
-locket==1.0.0
-lockfile==0.12.2
-lxml==5.3.0
-Markdown==3.7
-markdown-it-py==3.0.0
-MarkupSafe==3.0.2
-matplotlib==3.9.2
-matplotlib-inline==0.1.7
-mccabe==0.7.0
-mdurl==0.1.2
-mistune==3.0.2
-ml-dtypes==0.2.0
-monotonic==1.6
-mpmath==1.3.0
-multidict==6.1.0
-multiprocess==0.70.15
-nbclient==0.10.0
-nbconvert==7.16.4
-nbformat==5.10.4
-nest-asyncio==1.6.0
-notebook==7.0.6
-notebook_shim==0.2.4
-numba==0.60.0
-numpy==1.25.2
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==8.9.2.26
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-nccl-cu12==2.18.1
-nvidia-nvjitlink-cu12==12.6.68
-nvidia-nvtx-cu12==12.1.105
-oauth2client==4.1.3
-opencv-python==4.10.0.84
-optimum==1.22.0
-optimum[neuronx]==1.22.0
-orjson==3.10.7
-overrides==7.7.0
-packaging
-pandas==2.2.3
-pandocfilters==1.5.1
-papermill==2.6.0
-parsel==1.9.1
-parso==0.8.4
-partd==1.4.2
-peft==0.13.2
-pexpect==4.9.0
-pgzip==0.3.5
-pillow==10.4.0
-pip-tools==7.4.1
-pipenv==2024.0.2
-platformdirs==4.3.3
-plotly==5.24.1
-pluggy==1.5.0
-posthog==3.7.0
-prometheus-fastapi-instrumentator==7.0.0
-prometheus_client==0.21.0
-prompt_toolkit==3.0.47
-propcache==0.2.0
-Protego==0.3.1
-protobuf==5.28.2
-psutil==6.1.0
-ptyprocess==0.7.0
-pure_eval==0.2.3
-pyarrow==17.0.0
-pyarrow-hotfix==0.6
-pyasn1==0.6.1
-pyasn1_modules==0.4.1
-pycparser==2.22
-pydantic==2.9.2
-pydantic_core==2.23.4
-PyDispatcher==2.0.7
-Pygments==2.18.0
-pylint==3.2.7
-pyOpenSSL==24.2.1
-pyparsing==3.1.4
-pyproject_hooks==1.1.0
-PySocks==1.7.1
-pytest==8.3.3
-python-daemon==3.0.1
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-json-logger==2.0.7
-pytz==2024.2
-PyYAML==6.0.2
-pyzmq==26.2.0
-queuelib==1.7.0
-referencing==0.35.1
-regex==2024.9.11
-requests
-requests-file==2.1.0
-requests-toolbelt==1.0.0
-requests-unixsocket==0.3.0
-responses==0.18.0
-rfc3339-validator==0.1.4
-rich==13.9.2
-rpds-py==0.20.0
-rsa==4.7.2
-ruamel.yaml==0.18.6
-ruamel.yaml.clib==0.2.8
-s3transfer==0.10.2
-safetensors==0.4.5
-safety==2.3.5
-scikit-learn==1.5.2
-scipy==1.11.2
-Scrapy==2.11.2
-seaborn==0.13.2
-Send2Trash==1.8.3
-sentence-transformers==3.3.0
-sentencepiece==0.2.0
-service-identity==24.1.0
-shap==0.46.0
-shellingham==1.5.4
-six==1.16.0
-slicer==0.0.8
-sniffio==1.3.1
-soundfile==0.12.1
-soupsieve==2.6
-stack-data==0.6.3
-starlette==0.40.0
-sympy==1.13.3
-tenacity==9.0.0
-tensorboard==2.18.0
-tensorboard-data-server==0.7.2
-terminado==0.18.1
-threadpoolctl==3.5.0
-tinycss2==1.3.0
-tldextract==5.1.2
-tokenizers==0.19.*
-tomli==2.0.1
-tomlkit==0.13.2
-toolz==0.12.1
-torch==2.1.2
-# torch-xla==2.1.4
-torchvision==0.16.2
-tornado==6.4.1
-tqdm==4.66.5
-traitlets==5.14.3
-triton==2.1.0
-Twisted==24.7.0
-typer==0.12.5
-types-python-dateutil==2.9.0.20240906
-typing_extensions==4.12.2
-tzdata==2024.2
-uri-template==1.3.0
-uritemplate==3.0.1
-urllib3==2.2.3
-uvicorn==0.32.0
-vine==5.1.0
-virtualenv==20.26.4
-w3lib==2.2.1
-watchfiles==0.24.0
-wcwidth==0.2.13
-webcolors==24.8.0
-webencodings==0.5.1
-websocket-client==1.8.0
-websockets==13.1
-Werkzeug==3.1.3
-wget==3.2
-widgetsnbextension==4.0.13
-xxhash==3.5.0
-yarl==1.15.5
-zipp==3.20.2
-zope.interface==7.0.3
-libneuronxla==2.0.4115.0
-transformers-neuronx==0.12.313
-torch-neuronx==2.1.2.2.3.0
-tensorboard-plugin-neuronx==2.6.63.0
-neuronx-cc==2.15.128.0+56dc5a86
-neuronx-distributed==0.9.0
-neuronx-distributed-training==1.0.0
-aws-neuronx-runtime-discovery==2.9
\ No newline at end of file