mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-24 17:49:42 +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:
@@ -775,6 +775,7 @@ class SpeculativeSampler(nn.Layer):
|
||||
share_inputs["reasoning_status"],
|
||||
share_inputs["output_padding_offset"],
|
||||
share_inputs["output_cum_offsets"],
|
||||
share_inputs["enable_thinking"],
|
||||
self.think_end_id,
|
||||
self.line_break_id,
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user