v0.10.0

• https://github.com/hughperkins/TensorFlow-Examples/blob/enforce-gpu/examples/2_BasicModels/linear_regression.py runs ok now :-) (a bit slow, but not monstrously slow, maybe 3-4 times slower than on CUDA)
• kernels cached between kernel launches
• bunch of behind-the-scenes ops added, like Cast
• memory and device name reported correctly now
• reduce_min working now
• softmax added