|
@@ -23,7 +23,12 @@ jobs:
|
|
|
pip install .
|
|
|
|
|
|
- name: Run tests
|
|
|
- run: METAL_XCODE=1 python3 -m exo.inference.test_inference_engine
|
|
|
+ run: |
|
|
|
+ # Check if cached files are present
|
|
|
+ ls ~/.cache/huggingface/hub/models--mlx-community--Meta-Llama-3-8B-Instruct-4bit/**/*
|
|
|
+
|
|
|
+ # Run unit tests
|
|
|
+ METAL_XCODE=1 python3 -m exo.inference.test_inference_engine
|
|
|
|
|
|
discovery_integration_test:
|
|
|
runs-on: macos-latest
|
|
@@ -42,9 +47,6 @@ 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=$!
|
|
@@ -105,6 +107,9 @@ jobs:
|
|
|
|
|
|
- name: Run chatgpt api integration test
|
|
|
run: |
|
|
|
+ # Check if cached files are present
|
|
|
+ ls ~/.cache/huggingface/hub/models--mlx-community--Meta-Llama-3-8B-Instruct-4bit/**/*
|
|
|
+
|
|
|
# Start first instance
|
|
|
DEBUG_DISCOVERY=9 DEBUG=9 python3 main.py --listen-port 5678 --broadcast-port 5679 --chatgpt-api-port 8000 --chatgpt-api-response-timeout-secs 1200 > output1.log 2>&1 &
|
|
|
PID1=$!
|