You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Are you using the Triton container or did you build it yourself?
Using Pre Build
To Reproduce
I. Build custom triton_python_backend_stub:
conda create -n python3.9-env python=3.9
conda activate python3.9-env
git clone https://github.com/triton-inference-server/python_backend -b r21.06
cd python_backend
mkdir build && cd build
/opt/cmake/bin/cmake -DTRITON_ENABLE_GPU=ON -DTRITON_BACKEND_REPO_TAG=r21.06 -DTRITON_COMMON_REPO_TAG=r21.06 -DTRITON_CORE_REPO_TAG=r21.06 -DCMAKE_INSTALL_PREFIX:PATH=pwd/install ..
make triton-python-backend-stub
Describe the models (framework, inputs, outputs), ideally include the model configuration file (if using an ensemble include the model configuration file for that as well).
N/A Expected behavior
It should generate triton-python-backend-stub without any issues.
The text was updated successfully, but these errors were encountered:
Looks like jfrog was running into some issues lately. Please try again with this change included and let us know if you still run into issues: triton-inference-server/python_backend@2bdb14c
Description
I built a custom Python 3.10 or 3.9 execution environment stub and followed the instructions (https://github.com/triton-inference-server/python_backend#using-custom-python-execution-environments), but failed to generate stub, using pre-built NGC Triton 23.12 container.
Tried with other lower Triton versions 23.10, 22.09 etc., and issue still persist.
The error is:
-- Using src='https://boostorg.jfrog.io/artifactory/main/release/1.76.0/source/boost_1_76_0.tar.gz'
-- [download 100% complete]
-- [download 9% complete]
-- [download 22% complete]
-- [download 34% complete]
-- [download 46% complete]
-- [download 58% complete]
-- [download 70% complete]
-- [download 82% complete]
-- [download 94% complete]
-- [download 100% complete]
-- verifying file...
file='/home/jupyter/triton/python_backend/build/boost-src/src/boost_1_76_0.tar.gz'
-- SHA256 hash of
/home/jupyter/triton/python_backend/build/boost-src/src/boost_1_76_0.tar.gz
does not match expected value
expected: '7bd7ddceec1a1dfdcbdb3e609b60d01739c38390a5f956385a12f3122049f0ca'
actual: '5e89103d9b70bba5c91a794126b169cb67654be2051f90cf7c22ba6893ede0ff'
-- Hash mismatch, removing...
-- Retry after 5 seconds (attempt #2) ...
-- Using src='https://boostorg.jfrog.io/artifactory/main/release/1.76.0/source/boost_1_76_0.tar.gz'
.....
[5 bytes data]
Mark bundle as not supporting multiuse
The requested URL returned error: 409 Conflict
Closing connection 1
[5 bytes data]
TLSv1.2 (OUT), TLS alert, close notify (256):
[2 bytes data]
make[3]: *** [CMakeFiles/boostorg.dir/build.make:110: boost-src/src/boostorg-stamp/boostorg-download] Error 1
make[2]: *** [CMakeFiles/Makefile2:249: CMakeFiles/boostorg.dir/all] Error 2
make[1]: *** [CMakeFiles/Makefile2:198: CMakeFiles/triton-python-backend-stub.dir/rule] Error 2
make: *** [Makefile:183: triton-python-backend-stub] Error 2
Triton Information
23.12
Are you using the Triton container or did you build it yourself?
Using Pre Build
To Reproduce
I. Build custom triton_python_backend_stub:
conda create -n python3.9-env python=3.9
conda activate python3.9-env
git clone https://github.com/triton-inference-server/python_backend -b r21.06
cd python_backend
mkdir build && cd build
/opt/cmake/bin/cmake -DTRITON_ENABLE_GPU=ON -DTRITON_BACKEND_REPO_TAG=r21.06 -DTRITON_COMMON_REPO_TAG=r21.06 -DTRITON_CORE_REPO_TAG=r21.06 -DCMAKE_INSTALL_PREFIX:PATH=pwd/install ..
make triton-python-backend-stub
Describe the models (framework, inputs, outputs), ideally include the model configuration file (if using an ensemble include the model configuration file for that as well).
N/A
Expected behavior
It should generate triton-python-backend-stub without any issues.
The text was updated successfully, but these errors were encountered: