why does ORTModelForCausalLM assume new input length is 1 when past_key_values is passed
cyh-ustc opened this issue · comments
cyh-ustc commented
def prepare_inputs_for_generation(self, input_ids, past_key_values=None, **kwargs):
if past_key_values is not None:
past_length = past_key_values[0][0].shape[2]
# Some generation methods already pass only the last input ID
if input_ids.shape[1] > past_length:
remove_prefix_length = past_length
else:
# Default to old behavior: keep only final ID
remove_prefix_length = input_ids.shape[1] - 1
input_ids = input_ids[:, remove_prefix_length:]
while in non-onnx modeling, it's not.
# Keep only the unprocessed tokens:
# 1 - If the length of the attention_mask exceeds the length of input_ids, then we are in a setting where
# some of the inputs are exclusively passed as part of the cache (e.g. when passing input_embeds as
# input)
if attention_mask is not None and attention_mask.shape[1] > input_ids.shape[1]:
input_ids = input_ids[:, -(attention_mask.shape[1] - past_length) :]
# 2 - If the past_length is smaller than input_ids', then input_ids holds all input tokens. We can discard
# input_ids based on the past_length.
elif past_length < input_ids.shape[1]:
input_ids = input_ids[:, past_length:]