ClearML/clearml-serving
1
0
Fork 0
mirror of https://github.com/clearml/clearml-serving synced 2025-01-31 02:46:54 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Improve error handling on missing tritonserver executable

Browse Source
This commit is contained in:
allegroai 2021-05-14 01:30:16 +03:00
parent 435c537bca
commit 34d435714f
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
clearml_serving/triton_helper.py
View File

@ -114,7 +114,12 @@ class TritonHelper(object):
cmd.append('--{}={}'.format(k, v))
print('Starting server: {}'.format(cmd))
proc = subprocess.Popen(cmd)
try:
proc = subprocess.Popen(cmd)
except FileNotFoundError:
raise ValueError(
"Triton Server Engine (tritonserver) could not be found!\n"
"Verify you running inside the `nvcr.io/nvidia/tritonserver` docker container")
base_freq = min(update_frequency_sec, metric_frequency_sec)
metric_tic = update_tic = time()
while True: