Update quickstart.md (#704)

* Update quickstart.md

* Update doxygen_mainpage.md

* Update doxygen_mainpage.md

* Update terminology.md

media/docs/doxygen_mainpage.md

@@ -33,7 +33,7 @@ CUTLASS 2.0 is a substantial refactoring from the previous version, intended to
 # Example CUTLASS GEMM
 
 The following illustrates an example function that defines a CUTLASS GEMM kernel
-with single-precision inputs and outputs. This is an exercpt from the CUTLASS SDK 
+with single-precision inputs and outputs. This is an excerpt from the CUTLASS SDK 
 [basic_gemm example](https://github.com/NVIDIA/cutlass/tree/master/examples/00_basic_gemm/basic_gemm.cu).
 
 ~~~~~~~~~~~~~~~~~~~~~{.cpp}

media/docs/quickstart.md

@@ -347,7 +347,7 @@ Note, the above could be simplified as follows using helper methods defined in `
 
 # CUTLASS Library
 
-The [CUTLASS Library](./tools/library) defines an API for managing and executing collections of compiled
+The [CUTLASS Library](../../tools/library) defines an API for managing and executing collections of compiled
 kernel instances and launching them from host code without template instantiations in client code.
 
 The host-side launch API is designed to be analogous to BLAS implementations for convenience, though its 

media/docs/terminology.md

@@ -41,7 +41,7 @@ contiguous and strided dimensions of a tile.
 **Rank**: number of dimensions in a multidimensional index space, array, tensor, or matrix. Consistent with 
   [C++ Standard Library](https://en.cppreference.com/w/cpp/types/rank)
 
-**Register**: in device code, registes are the most efficient storage for statically sized arrays of elements.
+**Register**: in device code, registers are the most efficient storage for statically sized arrays of elements.
   Arrays may be expected to be stored in registers if all accesses are made via constexpr indices or within
   fully unrolled loops.