redesign for faster cpu/gpu synch (#1869)

* redesign for faster cpu/gpu synch

* load + more async CPU

* use command encoder API and move more ops to use it

* make fence back-end generic + CPU only fence

* faster build

* fix async eval

* fixes + handle temporaries

* fix / improve cpu conv

* remove unused status, fix siblings

* fix extensions

* fix

* fix no cpu build

* format

* comments

* fix perf regression, remove unecessary abort

* fix events, task limit cpu

* fix waiting

* fix donation / temporaries in normalization

mlx/export.cpp

@@ -832,7 +832,7 @@ ImportedFunction::ImportedFunction(const std::string& file)
                 std::move(shape),
                 type,
                 std::make_shared<Load>(
-                    default_stream(default_device()), is_ptr, offset),
+                    default_stream(Device::cpu), is_ptr, offset),
                 {}));
             is.seek(offset + tape.back().nbytes());
             constants.insert({id, tape.back()});