Add a slice_set op. (#2193)

* Add a slice_set op.

* Add some testing.

* Add the dedicated kv-cache module.

* Derive debug and clone.

* Expose more kv-cache functions.

* Return the current data when appending.

* Use the new cache in the quantized phi3 model.

candle-nn/src/lib.rs

@@ -6,6 +6,7 @@ pub mod encoding;
 pub mod func;
 pub mod group_norm;
 pub mod init;
+pub mod kv_cache;
 pub mod layer_norm;
 pub mod linear;
 pub mod loss;