Skip to content

E2E Preset Test

E2E Preset Test #3

name: E2E Preset Test
on:
workflow_run:
workflows: ["Build and Push Preset Models"]
types:
- completed
workflow_dispatch:
inputs:
force-run-all:
type: boolean
default: false
description: "Test all models for E2E"
force-run-all-phi-models:
type: boolean
default: false
description: "Test all Phi models for E2E"
env:
GO_VERSION: "1.22"
BRANCH_NAME: ${{ github.head_ref || github.ref_name}}
FORCE_RUN_ALL: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.force-run-all == 'true' }}
FORCE_RUN_ALL_PHI: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.force-run-all-phi-models== 'true' }}
permissions:
id-token: write
contents: read
jobs:
determine-models:
if: github.event_name == 'workflow_dispatch' || github.event.workflow_run.conclusion == 'success'
runs-on: ubuntu-latest
environment: preset-env
outputs:
matrix: ${{ steps.affected_models.outputs.matrix }}
is_matrix_empty: ${{ steps.check_matrix_empty.outputs.is_empty }}
full_matrix: ${{ steps.images.outputs.full_matrix }}
steps:
- name: Checkout
uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # v4.1.7
with:
submodules: true
fetch-depth: 0
# This script should output a JSON array of model names
- name: Determine Affected Models
id: affected_models
run: |
PR_BRANCH=${{ env.BRANCH_NAME }} \
FORCE_RUN_ALL=${{ env.FORCE_RUN_ALL }} \
FORCE_RUN_ALL_PHI=${{ env.FORCE_RUN_ALL_PHI }} \
python3 .github/workflows/kind-cluster/determine_models.py
- name: Print Determined Models
run: |
echo "Output from determine_models: ${{ steps.affected_models.outputs.matrix }}"
- name: Check if Matrix is Empty
id: check_matrix_empty
run: |
if [ "${{ steps.affected_models.outputs.matrix }}" == "[]" ] || [ -z "${{ steps.affected_models.outputs.matrix }}" ]; then
echo "is_empty=true" >> $GITHUB_OUTPUT
else
echo "is_empty=false" >> $GITHUB_OUTPUT
fi
- name: Add Config info for Testing
if: steps.check_matrix_empty.outputs.is_empty == 'false'
id: images
run: |
# Read the additional configurations from e2e-preset-configs.json
CONFIGS=$(cat .github/e2e-preset-configs.json | jq -c '.matrix.image')
echo "CONFIGS:"
echo $CONFIGS
# Pseudocode for combining matrices
# COMBINED_MATRIX = []
# for model in MATRIX:
# for config in CONFIGS:
# if config['name'] == model['name']:
# combined = {**model, **config}
# COMBINED_MATRIX.append(combined)
# break
COMBINED_MATRIX=$(echo '${{ steps.affected_models.outputs.matrix }}' | jq --argjson configs "$CONFIGS" -c '
map(. as $model | $configs[] | select(.name == $model.name) | $model + .)
')
echo "full_matrix=$COMBINED_MATRIX" >> $GITHUB_OUTPUT
- name: Print Combined Matrix
if: steps.check_matrix_empty.outputs.is_empty == 'false'
run: |
echo "Combined Matrix:"
echo '${{ steps.images.outputs.full_matrix }}'
e2e-preset-tests:
needs: determine-models
if: needs.determine-models.outputs.is_matrix_empty == 'false' && (github.event_name == 'workflow_dispatch' || github.event.workflow_run.conclusion == 'success')
runs-on: ubuntu-latest
environment: preset-env
strategy:
fail-fast: false
matrix:
# Ex matrix element:
# {"name":"falcon-40b","type":"text-generation","version":"#",
# "runtime":"tfs","tag":"0.0.1","node-count":1,
# "node-vm-size":"Standard_NC96ads_A100_v4", "node-osdisk-size":400}
model: ${{fromJson(needs.determine-models.outputs.full_matrix)}}
steps:
- name: Checkout
uses: actions/checkout@v4.1.7
with:
submodules: true
fetch-depth: 0
- name: Set OSS Flag
run: echo "MODEL_IS_OSS=${{ matrix.model.OSS }}" >> $GITHUB_ENV
- name: 'Az CLI login'
uses: azure/login@v2.2.0
with:
client-id: ${{ secrets.AZURE_CLIENT_ID }}
tenant-id: ${{ secrets.AZURE_TENANT_ID }}
allow-no-subscriptions: true
- name: 'Set ACR Subscription'
run: az account set --subscription ${{secrets.AZURE_SUBSCRIPTION_ID}}
- name: Check if Image exists in ACR
id: check_image
run: |
ACR_NAME=${{ secrets.ACR_AMRT_USERNAME }}
IMAGE_NAME=${{ matrix.model.name }}
TAG=${{ matrix.model.tag }}
# Use '|| true' to prevent script from exiting with an error if the repository is not found
TAGS=$(az acr repository show-tags -n $ACR_NAME --repository $IMAGE_NAME --output tsv || true)
if [[ -z "$TAGS" ]]; then
echo "Image $IMAGE_NAME:$TAG or repository not found in $ACR_NAME."
echo "IMAGE_EXISTS=false" >> $GITHUB_OUTPUT
else
if echo "$TAGS" | grep -q "^$TAG$"; then
echo "IMAGE_EXISTS=true" >> $GITHUB_OUTPUT
else
echo "IMAGE_EXISTS=false" >> $GITHUB_OUTPUT
echo "Image $IMAGE_NAME:$TAG not found in $ACR_NAME."
fi
fi
- name: Exit if Image for testing does not exist
if: steps.check_image.outputs.IMAGE_EXISTS == 'false'
run: |
echo "Image doesn't exist in ACR, remember to build image for testing first (preset-image-build)"
exit 1
- name: Set up kubectl context
run: |
az aks get-credentials --resource-group llm-test --name GitRunner
- name: Get Nodepool Name
id: get_nodepool_name
run: |
NAME_SUFFIX=${{ matrix.model.name }}
NAME_SUFFIX_WITHOUT_DASHES=${NAME_SUFFIX//-/} # Removing all '-' symbols
if [ ${#NAME_SUFFIX_WITHOUT_DASHES} -gt 12 ]; then
TRUNCATED_NAME_SUFFIX=${NAME_SUFFIX_WITHOUT_DASHES:0:12}
else
TRUNCATED_NAME_SUFFIX=$NAME_SUFFIX_WITHOUT_DASHES
fi
echo "Nodepool Name: $TRUNCATED_NAME_SUFFIX"
echo "NODEPOOL_NAME=$TRUNCATED_NAME_SUFFIX" >> $GITHUB_OUTPUT
- name: Create Nodepool
run: |
NODEPOOL_EXIST=$(az aks nodepool show \
--name ${{ steps.get_nodepool_name.outputs.NODEPOOL_NAME }} \
--cluster-name GitRunner \
--resource-group llm-test \
--query 'name' -o tsv || echo "")
echo "NODEPOOL_EXIST: $NODEPOOL_EXIST"
if [ -z "$NODEPOOL_EXIST" ]; then
az aks nodepool add \
--name ${{ steps.get_nodepool_name.outputs.NODEPOOL_NAME }} \
--cluster-name GitRunner \
--resource-group llm-test \
--node-count ${{ matrix.model.node-count }} \
--node-vm-size ${{ matrix.model.node-vm-size }} \
--node-osdisk-size ${{ matrix.model.node-osdisk-size }} \
--labels pool=${{ steps.get_nodepool_name.outputs.NODEPOOL_NAME }} \
--node-taints sku=gpu:NoSchedule \
--aks-custom-headers UseGPUDedicatedVHD=true
else
NODEPOOL_STATE=$(az aks nodepool show \
--name ${{ steps.get_nodepool_name.outputs.NODEPOOL_NAME }} \
--cluster-name GitRunner \
--resource-group llm-test \
--query 'provisioningState' -o tsv)
echo "NODEPOOL_STATE: $NODEPOOL_STATE"
if [ "$NODEPOOL_STATE" != "Succeeded" ]; then
echo "Nodepool exists but is not in a Succeeded state. Please check manually."
exit 1
else
echo "Nodepool already exists and is in a running state."
fi
fi
- name: Create Service
run: kubectl apply -f presets/test/manifests/${{ matrix.model.name }}/${{ matrix.model.name }}-service.yaml
- name: Retrieve External Service IP
id: get_ip
run: |
while [[ -z $SERVICE_IP ]]; do
SERVICE_IP=$(kubectl get svc ${{ matrix.model.name }} -o=jsonpath='{.status.loadBalancer.ingress[0].ip}')
sleep 5
done
echo "Service IP is $SERVICE_IP"
echo "SERVICE_IP=$SERVICE_IP" >> $GITHUB_OUTPUT
- name: Get Resource Type
id: resource
run: |
RESOURCE_TYPE=$(echo "${{ matrix.model.name }}" | grep -q "llama" && echo "statefulset" || echo "deployment")
echo "RESOURCE_TYPE=$RESOURCE_TYPE" >> $GITHUB_OUTPUT
- name: Replace IP and Deploy Resource to K8s
run: |
sed -i "s/MASTER_ADDR_HERE/${{ steps.get_ip.outputs.SERVICE_IP }}/g" presets/test/manifests/${{ matrix.model.name }}/${{ matrix.model.name }}.yaml
sed -i "s/TAG_HERE/${{ matrix.model.tag }}/g" presets/test/manifests/${{ matrix.model.name }}/${{ matrix.model.name }}.yaml
sed -i "s/REPO_HERE/${{ secrets.ACR_AMRT_USERNAME }}/g" presets/test/manifests/${{ matrix.model.name }}/${{ matrix.model.name }}.yaml
kubectl apply -f presets/test/manifests/${{ matrix.model.name }}/${{ matrix.model.name }}.yaml
- name: Wait for Resource to be ready
run: |
kubectl rollout status ${{steps.resource.outputs.RESOURCE_TYPE}}/${{ matrix.model.name }} --timeout=1800s
- name: Check Adapter Loading from Logs
if: matrix.model.loads_adapter == true
run: |
POD_NAME=$(kubectl get pods -l app=${{ matrix.model.name }} -o jsonpath="{.items[0].metadata.name}")
kubectl logs $POD_NAME | grep "Adapter added:" | grep "${{ matrix.model.expected_adapter }}" || (echo "Adapter not loaded or incorrect adapter loaded" && exit 1)
- name: Test home endpoint
run: |
curl http://${{ steps.get_ip.outputs.SERVICE_IP }}:80/
- name: Test healthz endpoint
run: |
curl http://${{ steps.get_ip.outputs.SERVICE_IP }}:80/healthz
- name: Test inference endpoint
run: |
if [[ "${{ matrix.model.name }}" == *"llama"* && "${{ matrix.model.name }}" == *"-chat"* ]]; then
echo "Testing inference for ${{ matrix.model.name }}"
curl -X POST \
-H "Content-Type: application/json" \
-d '{
"input_data": {
"input_string": [
[
{
"role": "system",
"content": "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe."
},
{
"role": "user",
"content": "Write a brief birthday message to John"
}
]
]
}
}' \
http://${{ steps.get_ip.outputs.SERVICE_IP }}:80/chat
elif [[ "${{ matrix.model.name }}" == *"llama"* ]]; then
echo "Testing inference for ${{ matrix.model.name }}"
curl -X POST \
-H "Content-Type: application/json" \
-d '{
"prompts": [
"I believe the meaning of life is",
"Simply put, the theory of relativity states that ",
"A brief message congratulating the team on the launch: Hi everyone, I just ",
"Translate English to French: sea otter => loutre de mer, peppermint => menthe poivrée, plush girafe => girafe peluche, cheese =>"
],
"parameters": {
"max_gen_len": 128
}
}' \
http://${{ steps.get_ip.outputs.SERVICE_IP }}:80/generate
else
echo "Testing inference for ${{ matrix.model.name }}"
curl -X POST \
-H "accept: application/json" \
-H "Content-Type: application/json" \
-d '{
"prompt":"Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:",
"return_full_text": false,
"clean_up_tokenization_spaces": false,
"prefix": null,
"handle_long_generation": null,
"generate_kwargs": {
"max_length":200,
"min_length":0,
"do_sample":true,
"early_stopping":false,
"num_beams":1,
"num_beam_groups":1,
"diversity_penalty":0.0,
"temperature":1.0,
"top_k":10,
"top_p":1,
"typical_p":1,
"repetition_penalty":1,
"length_penalty":1,
"no_repeat_ngram_size":0,
"encoder_no_repeat_ngram_size":0,
"bad_words_ids":null,
"num_return_sequences":1,
"output_scores":false,
"return_dict_in_generate":false,
"forced_bos_token_id":null,
"forced_eos_token_id":null,
"remove_invalid_values":null
}
}' \
http://${{ steps.get_ip.outputs.SERVICE_IP }}:80/chat
fi
- name: Cleanup
if: always()
run: |
# Only proceed if RESOURCE_TYPE is set (else resource wasn't created)
if [ -n "${{ steps.resource.outputs.RESOURCE_TYPE }}" ]; then
# Use RESOURCE_TYPE from the previous step
RESOURCE_TYPE=${{ steps.resource.outputs.RESOURCE_TYPE }}
# Check and Delete K8s Resource (Deployment or StatefulSet)
if kubectl get $RESOURCE_TYPE ${{ matrix.model.name }} > /dev/null 2>&1; then
kubectl delete $RESOURCE_TYPE ${{ matrix.model.name }}
fi
fi
# Check and Delete K8s Service if it exists
if kubectl get svc ${{ matrix.model.name }} > /dev/null 2>&1; then
kubectl delete svc ${{ matrix.model.name }}
fi
# Check and Delete AKS Nodepool if it exists
if [ -n "${{ steps.get_nodepool_name.outputs.NODEPOOL_NAME }}" ]; then
NODEPOOL_EXIST=$(az aks nodepool show \
--name ${{ steps.get_nodepool_name.outputs.NODEPOOL_NAME }} \
--cluster-name GitRunner \
--resource-group llm-test \
--query 'name' -o tsv || echo "")
if [ -n "$NODEPOOL_EXIST" ]; then
az aks nodepool delete \
--name ${{ steps.get_nodepool_name.outputs.NODEPOOL_NAME }} \
--cluster-name GitRunner \
--resource-group llm-test
fi
fi