apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[fix] fix requests & block metrics (#4404)
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
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* [fix] fix requests & block metrics

* [chore] rename variables
This commit is contained in:
李泳桦
2025-10-15 11:49:24 +08:00
committed by GitHub
parent abb62624b8
commit ffe7af8a97
5 changed files with 20 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/output/token_processor.py
+5 -2
View File
@@ -421,9 +421,12 @@ class TokenProcessor:
if task_id in self.resource_manager.req_dict:
del self.resource_manager.req_dict[task_id]
task_used_block_num = sum([len(task.block_tables) if task else 0 for task in self.resource_manager.tasks_list])
# Update block metrics
num_blocks_used_by_tasks = sum(
[len(task.block_tables) if task else 0 for task in self.resource_manager.tasks_list]
)
main_process_metrics.available_gpu_block_num.set(
self.resource_manager.total_block_number() - task_used_block_num
self.resource_manager.total_block_number() - num_blocks_used_by_tasks
)
main_process_metrics.batch_size.set(
self.resource_manager.max_num_seqs - self.resource_manager.available_batch()