apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 00:57:33 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

polish code with new pre-commit rule (#2923)

Browse Source
This commit is contained in:
Zero Rains
2025-07-19 23:19:27 +08:00
committed by GitHub
parent b8676d71a8
commit 25698d56d1
424 changed files with 14307 additions and 13518 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
fastdeploy/metrics/work_metrics.py
View File

@@ -17,18 +17,14 @@
"""
metrics
"""
import os
import atexit
import shutil
from threading import Lock
from prometheus_client import Histogram, Counter
from prometheus_client import Counter, Histogram
from fastdeploy.metrics.metrics import build_1_2_5_buckets
class WorkMetricsManager(object):
"""Prometheus Metrics Manager handles all metric updates """
class WorkMetricsManager:
"""Prometheus Metrics Manager handles all metric updates"""
_initialized = False
@@ -39,26 +35,45 @@ class WorkMetricsManager(object):
return
self.e2e_request_latency = Histogram(
'fastdeploy:e2e_request_latency_seconds',
'End-to-end request latency (from request arrival to final response)',
"fastdeploy:e2e_request_latency_seconds",
"End-to-end request latency (from request arrival to final response)",
buckets=[
0.3, 0.5, 0.8, 1.0, 1.5, 2.0, 2.5, 5.0, 10.0, 15.0, 20.0, 30.0,
40.0, 50.0, 60.0, 120.0, 240.0, 480.0, 960.0, 1920.0, 7680.0
]
0.3,
0.5,
0.8,
1.0,
1.5,
2.0,
2.5,
5.0,
10.0,
15.0,
20.0,
30.0,
40.0,
50.0,
60.0,
120.0,
240.0,
480.0,
960.0,
1920.0,
7680.0,
],
)
self.request_params_max_tokens = Histogram(
name='fastdeploy:request_params_max_tokens',
documentation='Histogram of max_tokens parameter in request parameters',
buckets=build_1_2_5_buckets(33792)
name="fastdeploy:request_params_max_tokens",
documentation="Histogram of max_tokens parameter in request parameters",
buckets=build_1_2_5_buckets(33792),
)
self.prompt_tokens_total = Counter(
name="fastdeploy:prompt_tokens_total",
documentation="Total number of prompt tokens processed",
)
self.request_prompt_tokens = Histogram(
name='fastdeploy:request_prompt_tokens',
documentation='Number of prefill tokens processed.',
buckets=build_1_2_5_buckets(33792)
name="fastdeploy:request_prompt_tokens",
documentation="Number of prefill tokens processed.",
buckets=build_1_2_5_buckets(33792),
)
self._initialized = True