From 4436a1099db55ece184741ac4f2a0dd0ed4f7cb3 Mon Sep 17 00:00:00 2001 From: Daniel Han-Chen Date: Sat, 3 Feb 2024 01:50:48 +1100 Subject: [PATCH] Update llama.py --- unsloth/models/llama.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index e8b12a8407..d61dbf842b 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -141,8 +141,7 @@ def LlamaAttention_fast_forward_inference( self.paged_attention_V = self.paged_attention[:,1] 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])