diff --git a/server/Makefile b/server/Makefile
index dbc9b7ef..da5171b2 100644
--- a/server/Makefile
+++ b/server/Makefile
@@ -29,5 +29,5 @@ run-dev:
 	SAFETENSORS_FAST_GPU=1 python -m torch.distributed.run --nproc_per_node=2 text_generation_server/cli.py serve bigscience/bloom-560m --sharded
 
 export-requirements:
-	poetry export -o requirements_cuda.txt --extras bnb --without-hashes
+	poetry export -o requirements_cuda.txt --without-hashes
 	poetry export -o requirements_rocm.txt --without-hashes
diff --git a/server/requirements_cuda.txt b/server/requirements_cuda.txt
index 3bc40ded..4b2fbc24 100644
--- a/server/requirements_cuda.txt
+++ b/server/requirements_cuda.txt
@@ -1,5 +1,4 @@
 backoff==2.2.1 ; python_version >= "3.9" and python_version < "3.13"
-bitsandbytes==0.43.0 ; python_version >= "3.9" and python_version < "3.13"
 certifi==2024.2.2 ; python_version >= "3.9" and python_version < "3.13"
 charset-normalizer==3.3.2 ; python_version >= "3.9" and python_version < "3.13"
 click==8.1.7 ; python_version >= "3.9" and python_version < "3.13"
@@ -16,24 +15,8 @@ grpcio==1.62.1 ; python_version >= "3.9" and python_version < "3.13"
 hf-transfer==0.1.6 ; python_version >= "3.9" and python_version < "3.13"
 huggingface-hub==0.19.4 ; python_version >= "3.9" and python_version < "3.13"
 idna==3.6 ; python_version >= "3.9" and python_version < "3.13"
-jinja2==3.1.3 ; python_version >= "3.9" and python_version < "3.13"
 loguru==0.6.0 ; python_version >= "3.9" and python_version < "3.13"
-markupsafe==2.1.5 ; python_version >= "3.9" and python_version < "3.13"
-mpmath==1.3.0 ; python_version >= "3.9" and python_version < "3.13"
-networkx==3.2.1 ; python_version >= "3.9" and python_version < "3.13"
 numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13"
-nvidia-cublas-cu12==12.1.3.1 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.9" and python_version < "3.13"
-nvidia-cuda-cupti-cu12==12.1.105 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.9" and python_version < "3.13"
-nvidia-cuda-nvrtc-cu12==12.1.105 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.9" and python_version < "3.13"
-nvidia-cuda-runtime-cu12==12.1.105 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.9" and python_version < "3.13"
-nvidia-cudnn-cu12==8.9.2.26 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.9" and python_version < "3.13"
-nvidia-cufft-cu12==11.0.2.54 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.9" and python_version < "3.13"
-nvidia-curand-cu12==10.3.2.106 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.9" and python_version < "3.13"
-nvidia-cusolver-cu12==11.4.5.107 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.9" and python_version < "3.13"
-nvidia-cusparse-cu12==12.1.0.106 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.9" and python_version < "3.13"
-nvidia-nccl-cu12==2.19.3 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.9" and python_version < "3.13"
-nvidia-nvjitlink-cu12==12.4.99 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.9" and python_version < "3.13"
-nvidia-nvtx-cu12==12.1.105 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.9" and python_version < "3.13"
 opentelemetry-api==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
 opentelemetry-exporter-otlp-proto-grpc==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
 opentelemetry-exporter-otlp-proto-http==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
@@ -53,12 +36,9 @@ safetensors==0.4.2 ; python_version >= "3.9" and python_version < "3.13"
 scipy==1.12.0 ; python_version >= "3.9" and python_version < "3.13"
 sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13"
 setuptools==69.2.0 ; python_version >= "3.9" and python_version < "3.13"
-sympy==1.12 ; python_version >= "3.9" and python_version < "3.13"
 tokenizers==0.15.2 ; python_version >= "3.9" and python_version < "3.13"
-torch==2.2.1 ; python_version >= "3.9" and python_version < "3.13"
 tqdm==4.66.2 ; python_version >= "3.9" and python_version < "3.13"
 transformers==4.39.0 ; python_version >= "3.9" and python_version < "3.13"
-triton==2.2.0 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version < "3.12" and python_version >= "3.9"
 typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
 typing-extensions==4.10.0 ; python_version >= "3.9" and python_version < "3.13"
 urllib3==2.2.1 ; python_version >= "3.9" and python_version < "3.13"