Fix for the batch dim in the quantized matmul example. (#2073)

* Fix for the batch dim in the quantized matmul example.

* Enable more tests on cuda.

* Add a test for qmm with a batch.

* Fix the zeros-dim test on metal.

candle-core/src/metal_backend/device.rs

@@ -283,5 +283,5 @@ impl MetalDevice {
 }
 
 fn buf_size(size: NSUInteger) -> NSUInteger {
-    (size - 1).next_power_of_two() as NSUInteger
+    size.saturating_sub(1).next_power_of_two() as NSUInteger
 }