Fast Hadamard Transform (#1249)

* Working hadamard for powers of 2

* working for m*2^k

* add scale and check contiguity

* add size check

* clean up

* fix test

* add grads + vmap

* gpu only

* skip on linux

* test typo

* add cpu impl

* remove gpu only tests

* fix linux build + add is_equivalent

mlx/backend/metal/jit/includes.h

@@ -18,6 +18,7 @@ const char* binary();
 const char* binary_two();
 const char* copy();
 const char* fft();
+const char* hadamard();
 const char* quantized();
 const char* ternary();
 const char* scan();