mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-24 01:29:57 +08:00
[Others] Support constrained decoding when enable_thinking is false (#6248)
* support constrained decoding when enable_thinking is false * fix * fix * fix
This commit is contained in:
@@ -243,6 +243,7 @@ def reasoning_phase_token_constraint(
|
||||
reasoning_status: paddle.Tensor,
|
||||
output_padding_offset: paddle.Tensor,
|
||||
output_cum_offsets: paddle.Tensor,
|
||||
enable_thinking: paddle.Tensor,
|
||||
think_end_id: int,
|
||||
line_break_id: int,
|
||||
):
|
||||
@@ -263,6 +264,7 @@ def reasoning_phase_token_constraint(
|
||||
reasoning_status,
|
||||
output_padding_offset,
|
||||
output_cum_offsets,
|
||||
enable_thinking,
|
||||
think_end_id,
|
||||
line_break_id,
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user