More accelerate optimizations (#427)

* Add more tracing to the whisper example.

* Support accelerate in more examples.

* Use accelerate for pointwise functions.

* Use accelerate for binary operations too.

* Bugfix for binary operation: use the rhs before the lhs.

candle-examples/examples/falcon/main.rs

@@ -1,5 +1,8 @@
 // TODO: Add an offline mode.
 
+#[cfg(feature = "accelerate")]
+extern crate accelerate_src;
+
 #[cfg(feature = "mkl")]
 extern crate intel_mkl_src;