From a15ffc95e03358ff0cca67520462262c9067261c Mon Sep 17 00:00:00 2001 From: Daniel Han-Chen Date: Sat, 3 Feb 2024 01:48:03 +1100 Subject: [PATCH] Update llama.py --- unsloth/models/llama.py | 1 + 1 file changed, 1 insertion(+) diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index 7e68d07df5..e8b12a8407 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -142,6 +142,7 @@ def LlamaAttention_fast_forward_inference( self.attention.resize_((bsz, n_heads, 1, self.attention.shape[-1]+KV_CACHE_INCREMENT)) pass + print(1) Qn = fast_linear_forward(self.q_proj, Xn, out = self.temp_QA[0]) Kn = fast_linear_forward(self.k_proj, Xn, out = self.temp_KV[0]) Vn = fast_linear_forward(self.v_proj, Xn, out = self.temp_KV[1])