diff --git a/vllm/model_executor/model_loader/weight_utils.py b/vllm/model_executor/model_loader/weight_utils.py index 4ce9394b3..44dcd076e 100644 --- a/vllm/model_executor/model_loader/weight_utils.py +++ b/vllm/model_executor/model_loader/weight_utils.py @@ -80,7 +80,18 @@ def enable_hf_transfer(): pass -enable_hf_transfer() +def enable_xet_high_performance(): + """automatically activates xet high performance mode""" + if "HF_XET_HIGH_PERFORMANCE" not in os.environ: + huggingface_hub.constants.HF_XET_HIGH_PERFORMANCE = True + + +if hasattr(huggingface_hub.constants, "HF_XET_HIGH_PERFORMANCE"): + # Transformers v5 + enable_xet_high_performance() +else: + # Transformers v4 + enable_hf_transfer() class DisabledTqdm(tqdm):