Avoid a contiguous call in the quantized phi 3 model. (#2209)

* Simplify the KvCache api.

* Avoid a contiguous call in the quantized phi3 model.

1 files changed, 1 insertions, 1 deletions

diff --git a/candle-transformers/src/models/quantized_phi3.rs b/candle-transformers/src/models/quantized_phi3.rs
index f9b55d9d..257ad983 100644
--- a/candle-transformers/src/models/quantized_phi3.rs
+++ b/candle-transformers/src/models/quantized_phi3.rs
@@ -146,7 +146,7 @@ impl LayerWeights {
             };
             let att = candle_nn::ops::softmax_last_dim(&att)?;
             // Convert to contiguous as matmul doesn't support strided vs for now.
-            att.matmul(&v.contiguous()?)?
+            att.matmul(&v)?
         };
         let y = y.transpose(1, 2)?.reshape(&[b_sz, seq_len, n_embd])?;
         let y = self.attn_output.forward(&y)?;