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/quantized/cuda.rs

@@ -464,7 +464,7 @@ impl QCudaStorage {
                 /* x_rows */ n,
                 /* x_cols */ k,
                 /* y_rows */ k,
-                /* y_cols */ m,
+                /* y_cols */ b * m,
                 self.device(),
             )?
         };