Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Commitb13a5a9

Browse files
authored
[None][chore] Add tests for non-existent and completed request cancellation (#6840)
Signed-off-by: Aurelien Chartier <2567591+achartier@users.noreply.github.com>
1 parent5c2f0fd commitb13a5a9

File tree

2 files changed

+121
-0
lines changed

2 files changed

+121
-0
lines changed

‎tests/integration/defs/triton_server/test_triton_llm.py‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3726,6 +3726,12 @@ def test_llmapi_backend(E2E_MODEL_NAME, DECOUPLED_MODE, TRITON_MAX_BATCH_SIZE,
37263726
output=venv_check_output(llm_backend_venv,run_cmd)
37273727
assert'Request is cancelled'inoutput
37283728

3729+
# Test request cancellation for non-existing request and completed request
3730+
run_cmd= [
3731+
f"{llm_backend_repo_root}/tools/tests/test_llmapi_cancel.py"
3732+
]
3733+
output=venv_check_output(llm_backend_venv,run_cmd)
3734+
37293735

37303736
@pytest.mark.parametrize("E2E_MODEL_NAME", ["ensemble","tensorrt_llm_bls"])
37313737
@pytest.mark.parametrize("ACCUMULATE_TOKEN", ["False"])
Lines changed: 115 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,115 @@
1+
#!/usr/bin/env python
2+
# Copyright 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
3+
#
4+
# Redistribution and use in source and binary forms, with or without
5+
# modification, are permitted provided that the following conditions
6+
# are met:
7+
# * Redistributions of source code must retain the above copyright
8+
# notice, this list of conditions and the following disclaimer.
9+
# * Redistributions in binary form must reproduce the above copyright
10+
# notice, this list of conditions and the following disclaimer in the
11+
# documentation and/or other materials provided with the distribution.
12+
# * Neither the name of NVIDIA CORPORATION nor the names of its
13+
# contributors may be used to endorse or promote products derived
14+
# from this software without specific prior written permission.
15+
#
16+
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
17+
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18+
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
19+
# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
20+
# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
21+
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
22+
# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
23+
# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
24+
# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
25+
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
26+
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
27+
28+
importos
29+
importsys
30+
fromfunctoolsimportpartial
31+
32+
importnumpyasnp
33+
fromtritonclientimportgrpcasgrpcclient
34+
fromtritonclient.utilsimportInferenceServerException
35+
36+
sys.path.append(os.path.dirname(os.path.abspath(__file__))+'/..')
37+
fromllmapi_clientimport (UserData,_prepare_inputs,callback,
38+
prepare_stop_signals)
39+
40+
if__name__=="__main__":
41+
input_data=np.array([
42+
"The current time is",
43+
],dtype=object)
44+
output_len=100
45+
inputs=_prepare_inputs(input_data,output_len)
46+
47+
stop_inputs=prepare_stop_signals()
48+
request_id=1
49+
user_data=UserData()
50+
withgrpcclient.InferenceServerClient(
51+
url="localhost:8001",
52+
verbose=False,
53+
ssl=False,
54+
root_certificates=None,
55+
private_key=None,
56+
certificate_chain=None,
57+
)astriton_client:
58+
59+
# Send stop request for non-existing request
60+
triton_client.async_infer(
61+
"tensorrt_llm",
62+
stop_inputs,
63+
request_id=str(request_id),# Request does not exist yet
64+
callback=partial(callback,user_data),
65+
parameters={'Streaming':False})
66+
67+
result=user_data._completed_requests.get()
68+
assertisinstance(result,InferenceServerException)
69+
assertresult.status()=="StatusCode.CANCELLED"
70+
71+
# Send actual request
72+
infer_response=triton_client.async_infer(
73+
"tensorrt_llm",
74+
inputs,
75+
request_id=str(request_id),
76+
callback=partial(callback,user_data),
77+
parameters={'Streaming':False})
78+
79+
result=user_data._completed_requests.get()
80+
print(
81+
f'Output text:{result.as_numpy("text_output")[0].decode("utf-8")}')
82+
83+
# Cancel request after it is completed
84+
infer_response.cancel()
85+
86+
# Send stop request for completed request
87+
triton_client.async_infer("tensorrt_llm",
88+
stop_inputs,
89+
request_id=str(request_id),
90+
callback=partial(callback,user_data),
91+
parameters={'Streaming':False})
92+
93+
cancel_result=user_data._completed_requests.get()
94+
assertisinstance(cancel_result,InferenceServerException)
95+
assertcancel_result.status()=="StatusCode.CANCELLED"
96+
97+
# Send a second request to check if server is still healthy
98+
infer_response_2=triton_client.async_infer(
99+
"tensorrt_llm",
100+
inputs,
101+
request_id=str(request_id+1),
102+
callback=partial(callback,user_data),
103+
parameters={'Streaming':False})
104+
105+
# Get result of second request
106+
result_2=user_data._completed_requests.get()
107+
print('Got completed request')
108+
109+
print(
110+
f'Output text:{result_2.as_numpy("text_output")[0].decode("utf-8")}'
111+
)
112+
113+
# Check that both results match
114+
assertnp.array_equal(result.as_numpy("text_output"),
115+
result_2.as_numpy("text_output"))

0 commit comments

Comments
 (0)

[8]ページ先頭

©2009-2025 Movatter.jp