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

[tgi] Add more models to TGI test pipeline #695

Merged
merged 1 commit into from
May 10, 2023
+36 −6
Merged

[tgi] Add more models to TGI test pipeline #695

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
42 changes: 36 additions & 6 deletions .github/workflows/hf_tgi_integration.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,15 +57,45 @@ jobs:
REGISTRY: ${{ steps.login-ecr.outputs.registry }}
run: |
HF_MODEL_ID=bigscience/bloom-560m && \
SM_NUM_GPUS=2 && \
TGI_VERSION=0.5.0 && \
docker run --gpus all --shm-size 1g -itd --rm -p 8080:8080 \
SM_NUM_GPUS=4 && \
TGI_VERSION=$TGI_VERSION && \
docker run --gpus all --shm-size 2g -itd --rm -p 8080:8080 \
-e SM_NUM_GPUS=$SM_NUM_GPUS -e HF_MODEL_ID=$HF_MODEL_ID ${REGISTRY}/djl-serving:tgi-${TGI_VERSION}
sleep 90
sleep 30
ret=$(curl http://localhost:8080/invocations -X POST \
-d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17}}' \
-d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":128}}' \
-H 'Content-Type: application/json')
[[ $ret != '[{"generated_text":"What is Deep Learning? Deep learning is a set of computer algorithms that learn a set of data, in a"}]' ]] && exit 1
[[ $ret != "[{\"generated_text\":\"What is Deep Learning?"* ]] && exit 1
docker rm -f $(docker ps -aq)
- name: Test gpt-neox-20b
env:
REGISTRY: ${{ steps.login-ecr.outputs.registry }}
run: |
HF_MODEL_ID=EleutherAI/gpt-neox-20b && \
SM_NUM_GPUS=4 && \
TGI_VERSION=$TGI_VERSION && \
docker run --gpus all --shm-size 2g -itd --rm -p 8080:8080 \
-e SM_NUM_GPUS=$SM_NUM_GPUS -e HF_MODEL_ID=$HF_MODEL_ID ${REGISTRY}/djl-serving:tgi-${TGI_VERSION}
sleep 120
ret=$(curl http://localhost:8080/invocations -X POST \
-d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":128}}' \
-H 'Content-Type: application/json')
[[ $ret != "[{\"generated_text\":\"What is Deep Learning?"* ]] && exit 1
docker rm -f $(docker ps -aq)
- name: Test flan-t5-xxl
env:
REGISTRY: ${{ steps.login-ecr.outputs.registry }}
run: |
HF_MODEL_ID=google/flan-t5-xxl && \
SM_NUM_GPUS=4 && \
TGI_VERSION=$TGI_VERSION && \
docker run --gpus all --shm-size 2g -itd --rm -p 8080:8080 \
-e SM_NUM_GPUS=$SM_NUM_GPUS -e HF_MODEL_ID=$HF_MODEL_ID ${REGISTRY}/djl-serving:tgi-${TGI_VERSION}
sleep 180
ret=$(curl http://localhost:8080/invocations -X POST \
-d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":128}}' \
-H 'Content-Type: application/json')
[[ $ret != "[{\"generated_text\""* ]] && exit 1
docker rm -f $(docker ps -aq)
- name: On fail step
if: ${{ failure() }}
Expand Down