Skip to content
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.

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

Documentation: tutorial-torchserve-neuronx misses literalinclude display #1085

Open
xasima opened this issue Jan 9, 2025 · 1 comment
Open

Comments

@xasima
Copy link

xasima commented Jan 9, 2025

Web documentation on tutorial-torchserve-neuronx doesn't show torch-model-archiver command. It stops on 'Run the following commands in your terminal'.

tutorial-torchserve-neuronx.rst

appropriate file 
.. literalinclude:: tutorial_source_instructions/run_torchserve_u20.sh
    :language: bash
    :lines: 12-16

supposed to include run_torchserve_u20.sh
content

mkdir model_store
MAX_LENGTH=$(jq '.max_length' config.json)
BATCH_SIZE=$(jq '.batch_size' config.json)
MODEL_NAME=bert-max_length$MAX_LENGTH-batch_size$BATCH_SIZE
torch-model-archiver --model-name "$MODEL_NAME" --version 1.0 --serialized-file ./bert_neuron_b6.pt --handler "./handler_bert_neuronx.py" --extra-files "./config.json" --export-path model_store

Screenshot:
Screenshot 2025-01-09 at 12 37 04

@xasima xasima changed the title Documentation: tutorial-torchserve-neuronx miss proper command display Documentation: tutorial-torchserve-neuronx misses literalinclude display Jan 9, 2025
@karthickgopalswamy
Copy link
Contributor

thanks for filing this. Will take a look

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants