Skip to content

Issues: aws/sagemaker-inference-toolkit

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

33 Open 11 Closed
33 Open 11 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Is streaming supported?
#137 opened Mar 22, 2024 by inf3rnus
Add support for downloading inference script and code (entry_point) from s3
#136 opened Jan 21, 2024 by urirosenberg
Triton container documentation implies py38
#134 opened Nov 17, 2023 by david-waterworth
psutil 5.9.6 seems to be throwing ZombieProcess when retrieving the mms process
#132 opened Oct 23, 2023 by charlietruong-wk
5
Enhancing Multi-Model Server Logging Support - JSON Format Integration
#131 opened Jul 25, 2023 by ViliamSerecun
Tensorflow Inference toolkit
#128 opened Jun 13, 2023 by vincentvic
Support for parquet encoder and decoder
#127 opened Jun 13, 2023 by lorenzwalthert
Support user-defined batch inference logic
#123 opened Apr 26, 2023 by dgcnz
Document default_pre_model_fn and default_model_warmup_fn
#117 opened Oct 21, 2022 by l3ku
stop_server function
#116 opened Oct 18, 2022 by Duncan-Haywood
Long Model Loading times in Multimodel Server
#113 opened Sep 26, 2022 by AlexRaschl
Support CustomAttributes in script mode (for PyTorch, HuggingFace, etc)
#110 opened Aug 17, 2022 by athewsey
1
Add (and test) Support for Python 3.8
#107 opened May 17, 2022 by ddluke
Include "Requires-Python" in source distributions
#106 opened May 17, 2022 by ddluke
Issue attaching eia device for huggingface transformers roBERTa model
#100 opened Feb 8, 2022 by kjhenner
Custom model_fn function not found when extending the PyTorch inference container
#86 opened Jun 22, 2021 by e13h
Default output function encodes results to JSON and that seems to add to response latency.
#84 opened Mar 30, 2021 by vdantu
1
In a multi-model scenario pass model name as argument to input_fn() and output_fn() type: enhancement
#77 opened Jan 21, 2021 by RajeshRamchander
SageMaker inference should be able to run as non-root user. type: enhancement
#72 opened Oct 13, 2020 by akulk314
1
3
Be able to change SageMaker endpoint log level contribution welcomed type: enhancement
#70 opened Sep 22, 2020 by oonisim
12
Warning: "Calling MMS with mxnet-model-server. Please move to multi-model-server." contribution welcomed type: enhancement
#69 opened Sep 11, 2020 by mb-dev
2
How to overwrite batch transform output in S3 type: documentation
#68 opened Sep 4, 2020 by BaoshengHeTR
5
Allow model_fn to get more arguments type: enhancement
#65 opened Aug 6, 2020 by ehsanmok
2
Enhance UX for inference type: enhancement type: UX
#64 opened Aug 6, 2020 by ehsanmok
logging in JSON format type: question
#59 opened Jul 17, 2020 by alext234
2
ProTip! no:milestone will show everything without a milestone.