Update llama.py

This commit is contained in:
Daniel Han-Chen 2024-02-02 22:22:42 +11:00
commit b33c92d1bd

View file

@ -681,8 +681,6 @@ import torch._dynamo.config
import torch._inductor.config
torch._inductor.config.coordinate_descent_tuning = True
torch._inductor.config.triton.unique_kernel_names = True
torch._inductor.config.fx_graph_cache = True # Experimental feature to reduce compilation times, will be on by default in future
# https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/modeling_llama.py#L825
@torch.compile(mode = "reduce-overhead", fullgraph = True)