0.1.6.post2 version update

Readme.md

@@ -13,13 +13,6 @@ To get the latest version, you can install the core library directly via ```pip
 
 Alternatively, clone the repo and run ```pip install .``` from this current folder. 
 
-#### Note
-For some reason, packages installed via ```pip install hqq``` don't build the CUDA kernels automatically. If you need to build the CUDA backend manually, you can do it as follows:
-
-```cd hqq/kernels && python setup_cuda.py install; cd ../../..; ```.
-
-Or simply use ```pip install git+https://github.com/mobiusml/hqq.git``` instead for the moment. 
-
 ### Basic Usage
 To perform quantization with HQQ, you simply need to replace the linear layers ( ```torch.nn.Linear```) as follows:
 ```Python

hqq/__init__.py

@@ -1,3 +1,3 @@
-__version__ = "0.1.6.post1"
+__version__ = "0.1.6.post2"
 __author__  = 'Dr. Hicham Badri'
 __credits__ = 'Mobius Labs GmbH'

setup.py

@@ -40,7 +40,7 @@ def run(self):
 
 setup(
     name="hqq",
-    version="0.1.6.post1",
+    version="0.1.6.post2",
     description="Half-Quadratic Quantization (HQQ)",
     url="https://github.com/mobiusml/hqq/",
     author="Dr. Hicham Badri",