apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[feat] add metrics for yiyan adapter (#3615)

Browse Source 
* [feat] add metrics for yiyan adapter (#3219)

* [feat] add metrics for yiyan adapter

* [fix] fix metrics num_requests_waiting and num_requests_running

* [fix] fix metrics gpu_cache_usage_perc

* [refactor] change where requests_number increases

* [chore] rename xxx_block_num as xxx_gpu_block_num, and update their values accordingly

* [chore] delete useless code

* [fix] fix error
This commit is contained in:
李泳桦
2025-08-28 21:16:58 +08:00
committed by GitHub
parent 6039cdc2c5
commit aad9d3564e
7 changed files with 186 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/splitwise/splitwise_connector.py
View File

@@ -24,6 +24,7 @@ import zmq
from fastdeploy import envs
from fastdeploy.engine.request import CompletionOutput, Request, RequestOutput
from fastdeploy.inter_communicator import EngineWorkerQueue
from fastdeploy.metrics.metrics import main_process_metrics
from fastdeploy.utils import get_logger
logger = get_logger("splitwise_connector", "splitwise_connector.log")
@@ -153,6 +154,7 @@ class SplitwiseConnector:
logger.warning(f"Send queue full for {addr}")
except Exception as e:
logger.error(f"Send to {addr} failed: {e}")
main_process_metrics.send_cache_failed_num.inc()
self._close_connection(addr)
except Exception as e: