apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fix limit_thinking bug (#5469)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Yuanle Liu
2025-12-10 11:56:35 +08:00
committed by GitHub
parent e9174f25e8
commit 1776d410d0
4 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
custom_ops/gpu_ops/limit_thinking_content_length_v1.cu
View File

@@ -33,7 +33,7 @@ __global__ void limit_thinking_content_length_kernel_v1(
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 == 2 && stop_flags[bid]) {
if (current_limit_think_status == 2 || stop_flags[bid]) {
return;
}

2
custom_ops/gpu_ops/limit_thinking_content_length_v2.cu
View File

@@ -35,7 +35,7 @@ __global__ void 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;
}

2
custom_ops/gpu_ops/speculate_decoding/speculate_limit_thinking_content_length_v1.cu
View File

@@ -39,7 +39,7 @@ __global__ void speculate_limit_thinking_content_length_kernel_v1(
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 == 2 && stop_flags[bid]) {
if (current_limit_think_status == 2 || stop_flags[bid]) {
return;
}

2
custom_ops/gpu_ops/speculate_decoding/speculate_limit_thinking_content_length_v2.cu
View File

@@ -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;
}