huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-23 16:02:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor: remove sagemaker entry-point

Browse Source 
The SageMaker image is built differently anyway.
This commit is contained in:
David Corvoysier 2025-02-19 09:00:54 +00:00
parent ae37890eef
commit 88a0948692
2 changed files with 0 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
Dockerfile.neuron
View File

@ -153,14 +153,6 @@ COPY --from=builder /usr/src/target/release/text-generation-launcher /usr/local/
COPY --from=pyserver /pyserver/build/dist dist
RUN pip install dist/text_generation_server*.tar.gz
# AWS Sagemaker compatible image
FROM neuron AS sagemaker
COPY backends/neuron/sagemaker-entrypoint.sh entrypoint.sh
RUN chmod +x entrypoint.sh
ENTRYPOINT ["./entrypoint.sh"]
# Final image
FROM neuron

22
backends/neuron/sagemaker-entrypoint.sh
View File

@ -1,22 +0,0 @@
#!/bin/bash
if [[ -z "${HF_MODEL_ID}" ]]; then
echo "HF_MODEL_ID must be set"
exit 1
fi
export MODEL_ID="${HF_MODEL_ID}"
if [[ -n "${HF_MODEL_REVISION}" ]]; then
export REVISION="${HF_MODEL_REVISION}"
fi
if [[ -n "${HF_MODEL_TRUST_REMOTE_CODE}" ]]; then
export TRUST_REMOTE_CODE="${HF_MODEL_TRUST_REMOTE_CODE}"
fi
if [[ -z "${MAX_BATCH_SIZE}" ]]; then
echo "MAX_BATCH_SIZE must be set to the model static batch size"
exit 1
fi
text-generation-launcher --port 8080