tvm
tvm copied to clipboard
[Refactorings]Few code optimizations
This PR makes a few code optimizations,
- utilize the
np.cumsum
API rather than inefficient for loops - use
multi dot
operator to perform matrix multiplication using a single API as opposed to two 'dot' APIs.
What do you think of the change?
@merrymercy @ezyang I am new to this project. Could you please help me to find a reviewer to this PR?