diff --git a/README.md b/README.md
index f598943d234320f0f451ccef99d3bf8998b79313..1844b17651d6c8eb87e38ccbbf0d8a036c152838 100644
--- a/README.md
+++ b/README.md
@@ -1,16 +1,14 @@
-# C++/CUDA Extensions in PyTorch
+# Usage
 
-An example of writing a C++ extension for PyTorch. See
-[here](http://pytorch.org/tutorials/advanced/cpp_extension.html) for the accompanying tutorial.
+## install
 
-There are a few "sights" you can metaphorically visit in this repository:
+```
+pip install .
+```
+
+## test
 
-- Inspect the C++ and CUDA extensions in the `cpp/` and `cuda/` folders,
-- Build C++ and/or CUDA extensions by going into the `cpp/` or `cuda/` folder and executing `python setup.py install`,
-- JIT-compile C++ and/or CUDA extensions by going into the `cpp/` or `cuda/` folder and calling `python jit.py`, which will JIT-compile the extension and load it,
-- Benchmark Python vs. C++ vs. CUDA by running `python benchmark.py {py, cpp, cuda} [--cuda]`,
-- Run gradient checks on the code by running `python grad_check.py {py, cpp, cuda} [--cuda]`.
-- Run output checks on the code by running `python check.py {forward, backward} [--cuda]`.
+- Run output and gradient checks on the code by running `python check.py `.
 
 
 ## prepare dataset