mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-04 16:22:57 +08:00
delete max-len (#2959)
This commit is contained in:
@@ -601,7 +601,6 @@ class GPUModelRunner(ModelRunnerBase):
|
||||
output_cum_offsets,
|
||||
output_padding_offset,
|
||||
) = pre_process(
|
||||
self.parallel_config.max_model_len,
|
||||
self.share_inputs["input_ids"],
|
||||
self.share_inputs["seq_lens_this_time"],
|
||||
self.speculative_decoding,
|
||||
|
Reference in New Issue
Block a user