|
@@ -17,6 +17,12 @@ jobs:
|
|
|
with:
|
|
|
python-version: '3.12'
|
|
|
|
|
|
+ - name: Cache huggingface hub models
|
|
|
+ uses: actions/cache@v3
|
|
|
+ with:
|
|
|
+ path: ~/.cache/huggingface/hub
|
|
|
+ key: ${{ runner.os }}-huggingface-hub-${{ hashFiles('~/.cache/huggingface/hub/**/*') }}-${{ github.job }}
|
|
|
+
|
|
|
- name: Install dependencies
|
|
|
run: |
|
|
|
python3 -m pip install --upgrade pip
|
|
@@ -25,7 +31,7 @@ jobs:
|
|
|
- name: Run tests
|
|
|
run: |
|
|
|
# Check if cached files are present
|
|
|
- ls ~/.cache/huggingface/hub/models--mlx-community--Meta-Llama-3-8B-Instruct-4bit/**/*
|
|
|
+ ls ~/.cache/huggingface/hub/models--mlx-community--Meta-Llama-3-8B-Instruct-4bit/**/* || true
|
|
|
|
|
|
# Run unit tests
|
|
|
METAL_XCODE=1 python3 -m exo.inference.test_inference_engine
|
|
@@ -88,7 +94,7 @@ jobs:
|
|
|
uses: actions/cache@v3
|
|
|
with:
|
|
|
path: ~/.cache/huggingface/hub
|
|
|
- key: ${{ runner.os }}-huggingface-hub-${{ hashFiles('~/.cache/huggingface/hub/**/*') }}
|
|
|
+ key: ${{ runner.os }}-huggingface-hub-${{ hashFiles('~/.cache/huggingface/hub/**/*') }}-${{ github.job }}
|
|
|
restore-keys: |
|
|
|
${{ runner.os }}-huggingface-hub-
|
|
|
|
|
@@ -96,7 +102,7 @@ jobs:
|
|
|
uses: actions/cache@v3
|
|
|
with:
|
|
|
path: ~/Library/Caches/tinygrad/downloads
|
|
|
- key: ${{ runner.os }}-tinygrad-downloads-${{ hashFiles('~/Library/Caches/tinygrad/downloads/**/*') }}
|
|
|
+ key: ${{ runner.os }}-tinygrad-downloads-${{ hashFiles('~/Library/Caches/tinygrad/downloads/**/*') }}-${{ github.job }}
|
|
|
restore-keys: |
|
|
|
${{ runner.os }}-tinygrad-downloads-
|
|
|
|
|
@@ -108,7 +114,7 @@ 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/**/*
|
|
|
+ ls ~/.cache/huggingface/hub/models--mlx-community--Meta-Llama-3-8B-Instruct-4bit/**/* || true
|
|
|
|
|
|
# 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 &
|