Skip to content

[BugFix]Fix limit thinking in speculate decoding #5466

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
freeliuzc wants to merge 1 commit into
base: develop
Choose a base branch
from
Open

[BugFix]Fix limit thinking in speculate decoding #5466

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion custom_ops/gpu_ops/speculate_decoding/speculate_limit_thinking_content_length_v2.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ __global__ void speculate_limit_thinking_content_length_kernel_v2(
if (max_think_len < 0) return;
int current_limit_think_status = limit_think_status[bid];
// 如果在回复阶段, 且已经触发停止标志, 则直接返回, 无需多余执行.
if (current_limit_think_status == 3 && stop_flags[bid]) {
if (current_limit_think_status == 3 || stop_flags[bid]) {
return;
}

Expand Down
Loading