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.

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

Jump to bottom

Remove flan-t5-xxl #829

Merged
merged 1 commit into from
Jun 12, 2023
Merged

Remove flan-t5-xxl #829

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 0 additions & 16 deletions .github/workflows/llm_integration.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -600,22 +600,6 @@ jobs:
working-directory: tests/integration
run: |
docker pull deepjavalibrary/djl-serving:$DJLSERVING_DOCKER_TAG
- name: Test flan-t5-xxl-partition
working-directory: tests/integration
run: |
sudo rm -rf models
python3 llm/prepare.py fastertransformer_handler_aot flan-t5-xxl
./launch_container.sh deepjavalibrary/djl-serving:$DJLSERVING_DOCKER_TAG $PWD/models deepspeed \
partition --model-dir /opt/ml/input/data/training
sudo mv $PWD/models/test/partition-test $PWD/models/
if grep -q /tmp/download.*-fp32-4-1 $PWD/models/partition-test/*-gpu/verify ; then echo "checkpoint files generated"; else exit 1; fi
- name: Test flan-t5-xxl-inference
working-directory: tests/integration
run: |
./launch_container.sh deepjavalibrary/djl-serving:$DJLSERVING_DOCKER_TAG $PWD/models deepspeed \
serve -m test=file:/opt/ml/model/partition-test/
python3 llm/client.py fastertransformer_raw flan-t5-xxl
docker rm -f $(docker ps -aq)
- name: Test t5-small-partition
working-directory: tests/integration
run: |
Expand Down
Loading