From dc2740416ba3940fadb588732fc25ab2f35bdcc6 Mon Sep 17 00:00:00 2001 From: Daniel Han-Chen Date: Fri, 2 Feb 2024 22:26:47 +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 127554ff19..b1d289497a 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -683,7 +683,7 @@ torch._inductor.config.coordinate_descent_tuning = True torch._inductor.config.triton.unique_kernel_names = True # https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/modeling_llama.py#L825 -@torch.compile(mode = "reduce-overhead", fullgraph = True) +@torch.compile(mode = "reduce-overhead") def LlamaModel_fast_forward_inference( self, input_ids,