From 4f4d5c80e0b4861519bc8caf88c03ea983313d2d Mon Sep 17 00:00:00 2001
From: Awni Hannun <awni@apple.com>
Date: Thu, 9 Jan 2025 12:21:31 -0800
Subject: [PATCH] some cleanup

---
 mlx_lm/models/llama.py | 2 --
 1 file changed, 2 deletions(-)

diff --git a/mlx_lm/models/llama.py b/mlx_lm/models/llama.py
index 739bc1a..4a789dc 100644
--- a/mlx_lm/models/llama.py
+++ b/mlx_lm/models/llama.py
@@ -69,8 +69,6 @@ class Attention(nn.Module):
         mask: Optional[mx.array] = None,
         cache: Optional[Any] = None,
     ) -> mx.array:
-        B, L, D = x.shape
-
         queries, keys, values = self.q_proj(x), self.k_proj(x), self.v_proj(x)
 
         # Prepare the queries, keys and values for the attention computation