aws / aws/amazon-sagemaker-examples

[Bug Report]SD on sagemaker triton error

Open
#3,780 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
11k
Forks
7k
Avg merge
8h 29m
Merged PRs (30d)
8

Description

I am running sd with triton bls via following notebook, and below error happens, triton server can't start correctly.

**Link to the notebook**
[link to notebook.](https://github.com/aws/amazon-sagemaker-examples/tree/main/sagemaker-triton/business_logic_scripting/stable_diffusion)

**Describe the bug**
UNAVAILABLE: Internal: archive_write_header() failed with error code = -25 error message is Can't create 'lib/python3.8/site-packages/onnx/backend/test/data/node/test_resize_downsample_sizes_nearest_not_larger/test_data_set_0/output_0.pb'

**To reproduce**
A clear, step-by-step set of instructions to reproduce the bug.
follow the notebook, it is easy to reproduce.

**Logs**
If applicable, add logs to help explain your problem.
You may also attach an `.ipynb` file to this issue if it includes relevant logs or output.

Contributor guide

Open the contributing guide

Research direction

Start by running the stable-diffusion notebook in sagemaker-triton/business_logic_scripting/stable_diffusion and reproduce the Triton startup failure. Inspect the archive_write_header error and the referenced ONNX test-data path; done means the notebook launches the Triton server without this error.

Written by the indexing model from the issue text.

Assessment

Tech stack
aws, jupyter-notebook, python
Domain
cloud, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.