|
@@ -42,6 +42,9 @@ jobs:
|
|
|
|
|
|
- name: Run discovery integration test
|
|
|
run: |
|
|
|
+ # Check if cached files are present
|
|
|
+ ls ~/.cache/huggingface/hub/models--mlx-community--Meta-Llama-3-8B-Instruct-4bit/**/*
|
|
|
+
|
|
|
# Start first instance
|
|
|
DEBUG_DISCOVERY=9 DEBUG=9 python3 main.py --listen-port 5678 --broadcast-port 5679 --chatgpt-api-port 8000 > output1.log 2>&1 &
|
|
|
PID1=$!
|
|
@@ -122,14 +125,6 @@ jobs:
|
|
|
"temperature": 0.7
|
|
|
}'
|
|
|
|
|
|
- curl -s http://localhost:8001/v1/chat/completions \
|
|
|
- -H "Content-Type: application/json" \
|
|
|
- -d '{
|
|
|
- "model": "llama-3-8b",
|
|
|
- "messages": [{"role": "user", "content": "Placeholder to load model..."}],
|
|
|
- "temperature": 0.7
|
|
|
- }'
|
|
|
-
|
|
|
response_1=$(curl -s http://localhost:8000/v1/chat/completions \
|
|
|
-H "Content-Type: application/json" \
|
|
|
-d '{
|