diff --git a/CHANGELOG.md b/CHANGELOG.md
index 766496c..04ff220 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -264,12 +264,13 @@ Deprecated:
 
 Features:
  - Added precompiled CUDA 11.8 binaries to support H100 GPUs without compilation #571
- - CUDA SETUP now no longer looks for libcuda and libcudart and relies PyTorch CUDA libraries. To manually override this behavior see: how_to_use_nonpytorch_cuda.md.
+ - CUDA SETUP now no longer looks for libcuda and libcudart and relies PyTorch CUDA libraries. To manually override this behavior see: how_to_use_nonpytorch_cuda.md. Thank you @rapsealk
 
 Bug fixes:
  - Fixed a bug where the default type of absmax was undefined which leads to errors if the default type is different than torch.float32. # 553
  - Fixed a missing scipy dependency in requirements.txt. #544
  - Fixed a bug, where a view operation could cause an error in 8-bit layers.
+ - Fixed a bug where CPU bitsandbytes would during the import. #593 Thank you @bilelomrani
 
 Documentation:
  - Improved documentation for GPUs that do not support 8-bit matmul. #529
diff --git a/bitsandbytes/cuda_setup/main.py b/bitsandbytes/cuda_setup/main.py
index 1d0cfae..1aaf9a0 100644
--- a/bitsandbytes/cuda_setup/main.py
+++ b/bitsandbytes/cuda_setup/main.py
@@ -101,17 +101,17 @@ class CUDASetup:
 
     def manual_override(self):
         if torch.cuda.is_available():
-            if 'CUDA_VERSION' in os.environ:
-                if len(os.environ['CUDA_VERSION']) > 0:
+            if 'BNB_CUDA_VERSION' in os.environ:
+                if len(os.environ['BNB_CUDA_VERSION']) > 0:
                     warn((f'\n\n{"="*80}\n'
-                          'WARNING: Manual override via CUDA_VERSION env variable detected!\n'
-                          'CUDA_VERSION=XXX can be used to load a bitsandbytes version that is different from the PyTorch CUDA version.\n'
-                          'If this was unintended set the CUDA_VERSION variable to an empty string: export CUDA_VERSION=\n'
+                          'WARNING: Manual override via BNB_CUDA_VERSION env variable detected!\n'
+                          'BNB_CUDA_VERSION=XXX can be used to load a bitsandbytes version that is different from the PyTorch CUDA version.\n'
+                          'If this was unintended set the BNB_CUDA_VERSION variable to an empty string: export BNB_CUDA_VERSION=\n'
                           'If you use the manual override make sure the right libcudart.so is in your LD_LIBRARY_PATH\n'
                           'For example by adding the following to your .bashrc: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:<path_to_cuda_dir/lib64\n'
-                          f'Loading CUDA version: CUDA_VERSION={os.environ["CUDA_VERSION"]}'
+                          f'Loading CUDA version: BNB_CUDA_VERSION={os.environ["BNB_CUDA_VERSION"]}'
                           f'\n{"="*80}\n\n'))
-                    self.binary_name = self.binary_name[:-6] + f'{os.environ["CUDA_VERSION"]}.so'
+                    self.binary_name = self.binary_name[:-6] + f'{os.environ["BNB_CUDA_VERSION"]}.so'
 
     def run_cuda_setup(self):
         self.initialized = True
@@ -237,10 +237,10 @@ def warn_in_case_of_duplicates(results_paths: Set[Path]) -> None:
             f"Found duplicate {CUDA_RUNTIME_LIBS} files: {results_paths}.. "
             "We select the PyTorch default libcudart.so, which is {torch.version.cuda},"
             "but this might missmatch with the CUDA version that is needed for bitsandbytes."
-            "To override this behavior set the CUDA_VERSION=<version string, e.g. 122> environmental variable"
+            "To override this behavior set the BNB_CUDA_VERSION=<version string, e.g. 122> environmental variable"
             "For example, if you want to use the CUDA version 122"
-            "CUDA_VERSION=122 python ..."
-            "OR set the environmental variable in your .bashrc: export CUDA_VERSION=122"
+            "BNB_CUDA_VERSION=122 python ..."
+            "OR set the environmental variable in your .bashrc: export BNB_CUDA_VERSION=122"
             "In the case of a manual override, make sure you set the LD_LIBRARY_PATH, e.g."
             "export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda-11.2")
         CUDASetup.get_instance().add_log_entry(warning_msg, is_warning=True)
diff --git a/how_to_use_nonpytorch_cuda.md b/how_to_use_nonpytorch_cuda.md
index f91dd23..7b717f4 100644
--- a/how_to_use_nonpytorch_cuda.md
+++ b/how_to_use_nonpytorch_cuda.md
@@ -24,21 +24,19 @@ wget https://raw.githubusercontent.com/TimDettmers/bitsandbytes/main/cuda_instal
 bash cuda install 117 ~/local 1 
 ```
 
-## Setting the environmental variables CUDA_HOME, CUDA_VERSION, and LD_LIBRARY_PATH
+## Setting the environmental variables BNB_CUDA_VERSION, and LD_LIBRARY_PATH
 
 To manually override the PyTorch installed CUDA version you need to set to variable, like so:
 
 ```bash
-export CUDA_HOME=<PATH>
-export CUDA_VERSION=<VERSION>
+export BNB_CUDA_VERSION=<VERSION>
 export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:<PATH>
 ```
 
 For example, to use the local install path from above:
 
 ```bash
-export CUDA_HOME=/home/tim/local/cuda-11.7
-export CUDA_VERSION=117
+export BNB_CUDA_VERSION=117
 export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/tim/local/cuda-11.7
 ```
 
diff --git a/setup.py b/setup.py
index 37f80f2..a3beb5e 100644
--- a/setup.py
+++ b/setup.py
@@ -18,7 +18,7 @@ def read(fname):
 
 setup(
     name=f"bitsandbytes",
-    version=f"0.40.1",
+    version=f"0.40.1.post1",
     author="Tim Dettmers",
     author_email="dettmers@cs.washington.edu",
     description="k-bit optimizers and matrix multiplication routines.",