aws sagemaker-pytorch-inference-toolkit issues

aws / sagemaker-pytorch-inference-toolkit

Toolkit for allowing inference and serving with PyTorch on SageMaker. Dockerfiles used for building SageMaker Pytorch Containers are at https://github.com/aws/deep-learning-containers.

Apache License 2.0

131 stars 69 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Ignore zombie processes when detecting TorchServe status

#166 namannandan closed 1 month ago
7
Zombie process exception

#165 5agado opened 1 month ago
4
Improve error logging when invoking custom handler methods

#164 namannandan closed 4 months ago
0
Improve debuggability during model load and inference failures

#163 namannandan closed 4 months ago
0
Fix dependency versions

#162 sachanub closed 7 months ago
0
Unpin dependency versions

#161 sachanub closed 7 months ago
0
Include 2.1.0 container for integration tests

#160 sachanub closed 7 months ago
0
Upgrade psutil version

#159 sachanub opened 8 months ago
0
Cleanup to remove EIA integration tests and other unused files/code

#158 sachanub closed 9 months ago
0
Migrate base inference toolkit scripts and unit tests

#157 sachanub closed 9 months ago
0
ModuleNotFoundError: Sagemaker only copies entry_point file to /opt/ml/code/ instead of the holy-cloned source code

#156 celsofranssa opened 9 months ago
0
Add new unit and integration tests

#155 sachanub closed 9 months ago
4
Fix integration tests and update Python versions

#154 sachanub closed 9 months ago
0
Dummy PR 2 - Include base inference toolkit

#153 sachanub closed 9 months ago
0
Dummy PR to understand PyTorch inference toolkit build process

#152 sachanub closed 9 months ago
1
remove unused file

#151 lxning closed 11 months ago
0
reuse sagemaker-inference's requirements.txt installation logic

#150 humanzz closed 11 months ago
0
Reuse the requirements.txt installation logic from sagemaker-inference-toolkit

#149 humanzz closed 11 months ago
0
Enable vmargs argument for torchserve

#148 carljeske opened 1 year ago
0
deprecation: deleting outdated docker file for pytorch-eia-1.3.1

#147 pravali96 opened 1 year ago
0
Enable telemetry.

#146 chen3933 closed 1 year ago
0
fix: Remove stale docker files

#145 ivan-khvostishkov opened 1 year ago
0
Add support for SAGEMAKER_MAX_PAYLOAD_IN_MB

#143 namannandan closed 1 year ago
2
Documentation for inference.py `transform_fn`

#142 david-waterworth opened 1 year ago
0
Incorrect reporting of memory utilisation

#141 david-waterworth opened 1 year ago
0
Modify log4j2.xml to remove dependency on javascript.

#140 chen3933 closed 1 year ago
0
fix_build

#139 chen3933 closed 1 year ago
1
fix_build

#138 chen3933 closed 1 year ago
0
Prepend `code_dir` to `sys.path` rather than `append`

#137 davidthomas426 opened 1 year ago
0
add vmargs=-XX:-UseContainerSupport in config

#136 lxning closed 1 year ago
3
Document TorchServe version compatibility

#135 davidthomas426 opened 1 year ago
2
Specify batch size for MME

#134 austinmw opened 1 year ago
0
[Question] Using model.mar with built-in handler script

#133 austinmw opened 1 year ago
0
configure min torchserve version dependency

#132 rohithkrn closed 1 year ago
0
Update PyTorch Inference toolkit to log telemetry metrics

#131 sachanub closed 1 year ago
0
Fix: Don't load default model in MME mode

#130 nskool closed 1 year ago
10
MMS mode in inference does not support in GPU instance

#129 holopekochan closed 1 year ago
0
Is this Dockerfile compatible with sagemaker elastic inference

#128 fymaterials98 opened 1 year ago
0
Multi gpu support

#127 waytrue17 opened 1 year ago
16
how to use gpu in sagemaker instance

#126 haiderasad opened 2 years ago
1
using cuda enabled pytorch image

#125 haiderasad opened 2 years ago
0
Document how to locally run the container

#124 ManuelVs opened 2 years ago
2
add environment variable "OMP_NUM_THREADS"

#123 lxning opened 2 years ago
0
Use an overriden transform function to support batch inference in pytorch

#122 nskool closed 1 year ago
5
Batch Inference does not work when using the default handler

#121 nskool opened 2 years ago
0
Test config change

#120 mseth10 opened 2 years ago
2
Update CI to use PyTorch 1.10

#119 mseth10 closed 2 years ago
16
pass model directory as input to torchserve

#118 mseth10 closed 2 years ago
80
Launch TorchServe without repackaging model contents

#117 fm1ch4 opened 2 years ago
5
No model logs from PyTorch 1.10 SageMaker endpoint

#116 setu4993 closed 1 year ago
2