creating a static library containing templates

Question

I'm developing static library for matrix operations using templates wherein we can perform basic matrix operations on various datatypes(short, int, long, long long, float, double, long double). But as far as I know when using templates, class declaration and definition can't be kept in separate files(.h and .cpp files). If this is the case how do I create the library without exposing my implementation code(only class syntax declaration and library has to be provided to an other user). This is what I've written so far

MatrixClass.h

#ifndef __MATRIXCLASS_H__
#define __MATRIXCLASS_H__

#include<iostream>
#include<vector>


template<typename T>
class CMatrix { 
public:
    CMatrix();
    ~CMatrix();

    unsigned long rows;
    unsigned long cols;

    std::vector<std::vector<T> > data;

    void setMatrixSize(unsigned long rows, unsigned long cols);
    void printMatrix();
    void add(CMatrix<T>& A, CMatrix<T>& B);
    void sub(CMatrix<T>& A, CMatrix<T>& B);
    void mul(CMatrix<T>& A, CMatrix<T>& B);
};


template<typename T>
CMatrix<T>::CMatrix() {
    this->rows = 0;
    this->cols = 0;

    data.clear();
}


template<typename T>
CMatrix<T>::~CMatrix() {
    this->rows = 0;
    this->cols = 0;

    data.clear();
}


template<typename T>
void CMatrix<T>::setMatrixSize(unsigned long rows, unsigned long cols) {
    this->rows = rows;
    this->cols = cols;

    data.clear();
    data.resize(cols, std::vector<T>(rows, 0));
}


template<typename T>
void CMatrix<T>::printMatrix() {
    for(unsigned long i = 0; i < rows; i++) {
        for(unsigned long j = 0; j < cols; j++) {
            std::cout << data.at(i).at(j) << "\t";
        }
        std::cout << std::endl;
    } 
}


template<typename T>
void CMatrix<T>::add(CMatrix<T>& A, CMatrix<T>& B) {
    if((A.rows == B.rows) && (A.cols == B.cols)) {
        for(unsigned long i = 0; i < rows; i++) {
            for(unsigned long j = 0; j < cols; j++) {
                data.at(i).at(j) = A.data.at(i).at(j) + B.data.at(i).at(j);
            }
        }
    }
}


template<typename T>
void CMatrix<T>::sub(CMatrix<T>& A, CMatrix<T>& B) {
    if((A.rows == B.rows) && (A.cols == B.cols)) {
        for(unsigned long i = 0; i < rows; i++) {
            for(unsigned long j = 0; j < cols; j++) {
                data.at(i).at(j) = A.data.at(i).at(j) - B.data.at(i).at(j);
            }
        }
    }
}


template<typename T>
void CMatrix<T>::mul(CMatrix<T>& A, CMatrix<T>& B) {
    if((A.cols == B.rows) && (rows == A.rows) && (cols == B.cols)) {
        for(unsigned long i = 0; i < A.rows; i++) {
            for(unsigned long j = 0; j < B.cols; j++) {
                for(unsigned long k = 0; k < A.cols; k++) {
                    data.at(i).at(j) += A.data.at(i).at(k) * B.data.at(k).at(j);
                }
            }
        }
    }
}

#endif