From 6d2bc97117d9d12d6fe254ffc0664cfb10cd04cb Mon Sep 17 00:00:00 2001 From: Daniel Han-Chen Date: Sun, 10 Mar 2024 14:08:38 +1100 Subject: [PATCH] Update llama.py --- unsloth/models/llama.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index 7ecb00af9e..30348b69c2 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -705,7 +705,7 @@ def CausalLM_fast_forward(fast_forward_inference): *args, **kwargs, ) -> Union[Tuple, CausalLMOutputWithPast]: - if False: #past_key_values is not None and hasattr(self.model.layers[0].self_attn, "paged_attention"): + if past_key_values is not None and hasattr(self.model.layers[0].self_attn, "paged_attention"): outputs = fast_forward_inference( self.model, input_ids,