From 947411823a9ebe1451313684a2c4eabf73e570ee Mon Sep 17 00:00:00 2001 From: amitraj Date: Thu, 12 Dec 2024 11:32:32 +0530 Subject: [PATCH] lint and format Signed-off-by: amitraj --- QEfficient/transformers/models/modeling_auto.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/QEfficient/transformers/models/modeling_auto.py b/QEfficient/transformers/models/modeling_auto.py index 59926754..05b62dcb 100644 --- a/QEfficient/transformers/models/modeling_auto.py +++ b/QEfficient/transformers/models/modeling_auto.py @@ -348,9 +348,9 @@ def generate( :device_id (List[int]): Ids of devices for running the qpc pass as [0] in case of normal model / [0, 1, 2, 3] in case of tensor slicing model ``optional`` Args: :runtime_ai100 (bool, optional): ``AI_100`` and ``PyTorch`` runtime is supported as of now. Defaults to ``True`` for ``AI_100`` runtime. - + """ - if runtime_ai100: + if runtime_ai100: if not isinstance(self.qpc_path, Path): raise TypeError("Please run compile API first!") generation_len = kwargs.pop("generation_len", None) @@ -365,7 +365,6 @@ def generate( else: inputs = tokenizer(prompts, return_tensors="pt", padding="max_length", max_length=seq_len) return self.model(**inputs) - class QEffAutoModel(QEFFTransformersBase):