[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638)
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
This commit is contained in:
Aryan Kumar
co-authored by
Aryan Kumar
Aryan Kumar
parent
8208536cd1
commit
8537dcd6de
@@ -0,0 +1,149 @@
|
||||
name: macOS MLX Smoke
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
branches: [main]
|
||||
paths:
|
||||
- ".github/workflows/ci-macos-mlx.yml"
|
||||
- "fastvideo/mlx_runtime/**"
|
||||
- "fastvideo/tests/mlx/**"
|
||||
- "fastvideo/tests/platforms/test_mps_vsa_error.py"
|
||||
- "fastvideo/platforms/mps.py"
|
||||
- "fastvideo/platforms/__init__.py"
|
||||
- "fastvideo/__init__.py"
|
||||
- "examples/inference/basic/mlx_*.py"
|
||||
- "fastvideo/benchmarks/mlx_*.py"
|
||||
- "pyproject.toml"
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
concurrency:
|
||||
group: macos-mlx-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
mlx-smoke:
|
||||
if: github.event_name == 'workflow_dispatch' || github.event.pull_request.draft != true
|
||||
runs-on: macos-15
|
||||
timeout-minutes: 25
|
||||
env:
|
||||
FASTVIDEO_ATTENTION_BACKEND: TORCH_SDPA
|
||||
TOKENIZERS_PARALLELISM: "false"
|
||||
MASTER_ADDR: localhost
|
||||
MASTER_PORT: "29513"
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.12"
|
||||
cache: pip
|
||||
|
||||
- uses: astral-sh/setup-uv@v3
|
||||
|
||||
- name: Install lightweight MLX smoke dependencies
|
||||
run: |
|
||||
uv pip install --system \
|
||||
--index-url https://download.pytorch.org/whl/cpu \
|
||||
torch==2.11.0 torchvision torchaudio
|
||||
uv pip install --system \
|
||||
pytest numpy scipy pillow imageio einops cloudpickle filelock \
|
||||
PyYAML diffusers huggingface_hub remote-pdb safetensors loguru mlx \
|
||||
"ftfy>=6.3.1" "opencv-python>=4.10.0.84" psutil "transformers>=5.0.0"
|
||||
|
||||
- name: Show Apple runtime
|
||||
run: |
|
||||
python - <<'PY'
|
||||
import platform
|
||||
import mlx.core as mx
|
||||
import torch
|
||||
|
||||
print("machine:", platform.machine())
|
||||
print("processor:", platform.processor())
|
||||
print("mlx default device:", mx.default_device())
|
||||
memory_size = mx.metal.device_info().get("memory_size") if mx.metal.is_available() else "metal unavailable"
|
||||
print("mlx memory_size:", memory_size)
|
||||
print("torch:", torch.__version__)
|
||||
print("torch mps available:", torch.backends.mps.is_available())
|
||||
PY
|
||||
|
||||
- name: Run MLX smoke tests
|
||||
run: |
|
||||
python -m pytest \
|
||||
fastvideo/tests/mlx/test_dmd_sampling.py \
|
||||
fastvideo/tests/mlx/test_memory_limits.py \
|
||||
fastvideo/tests/mlx/test_quant_capability.py \
|
||||
fastvideo/tests/mlx/test_mlx_dit_parity.py \
|
||||
fastvideo/tests/mlx/test_mlx_compile_parity.py \
|
||||
fastvideo/tests/mlx/test_mlx_checkpoint.py \
|
||||
fastvideo/tests/mlx/test_mlx_fastwan_benchmark.py \
|
||||
fastvideo/tests/mlx/test_taehv_decode.py \
|
||||
fastvideo/tests/mlx/test_frame_upsample.py \
|
||||
fastvideo/tests/mlx/test_mlx_fast_spatial.py \
|
||||
fastvideo/tests/mlx/test_mlx_refine.py \
|
||||
fastvideo/tests/mlx/test_mlx_prompt_to_video_decode.py \
|
||||
fastvideo/tests/mlx/test_mlx_wan22_prompt_cache_fingerprint.py \
|
||||
fastvideo/tests/mlx/test_wan22_sample.py \
|
||||
fastvideo/tests/mlx/test_windowed_attention.py \
|
||||
fastvideo/tests/mlx/test_mlx_rife_interpolation.py::test_rife_download_unavailable_has_specific_error \
|
||||
fastvideo/tests/mlx/test_mlx_rife_interpolation.py::test_rife_backend_regression_is_not_skip_eligible \
|
||||
fastvideo/tests/platforms/test_mps_vsa_error.py \
|
||||
-q
|
||||
|
||||
# Same tests on MLX's CPU backend. Hosted macOS runners are scarce and
|
||||
# slower to schedule; this Linux job gives fast PR signal on the identical
|
||||
# graph (the parity tests were designed to be backend-agnostic), while the
|
||||
# macOS job above stays the source of truth for Metal behavior.
|
||||
mlx-smoke-linux-cpu:
|
||||
if: github.event_name == 'workflow_dispatch' || github.event.pull_request.draft != true
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 20
|
||||
env:
|
||||
FASTVIDEO_ATTENTION_BACKEND: TORCH_SDPA
|
||||
TOKENIZERS_PARALLELISM: "false"
|
||||
MASTER_ADDR: localhost
|
||||
MASTER_PORT: "29513"
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.12"
|
||||
cache: pip
|
||||
|
||||
- uses: astral-sh/setup-uv@v3
|
||||
|
||||
- name: Install lightweight MLX smoke dependencies (CPU backend)
|
||||
run: |
|
||||
uv pip install --system \
|
||||
--index-url https://download.pytorch.org/whl/cpu \
|
||||
torch==2.11.0 torchvision torchaudio
|
||||
uv pip install --system \
|
||||
pytest numpy scipy pillow imageio einops cloudpickle filelock \
|
||||
PyYAML diffusers huggingface_hub remote-pdb safetensors loguru "mlx[cpu]" \
|
||||
"ftfy>=6.3.1" "opencv-python>=4.10.0.84" psutil "transformers>=5.0.0"
|
||||
|
||||
- name: Run MLX smoke tests (CPU backend)
|
||||
run: |
|
||||
python -m pytest \
|
||||
fastvideo/tests/mlx/test_dmd_sampling.py \
|
||||
fastvideo/tests/mlx/test_memory_limits.py \
|
||||
fastvideo/tests/mlx/test_quant_capability.py \
|
||||
fastvideo/tests/mlx/test_mlx_dit_parity.py \
|
||||
fastvideo/tests/mlx/test_mlx_compile_parity.py \
|
||||
fastvideo/tests/mlx/test_mlx_checkpoint.py \
|
||||
fastvideo/tests/mlx/test_mlx_fastwan_benchmark.py \
|
||||
fastvideo/tests/mlx/test_taehv_decode.py \
|
||||
fastvideo/tests/mlx/test_frame_upsample.py \
|
||||
fastvideo/tests/mlx/test_mlx_fast_spatial.py \
|
||||
fastvideo/tests/mlx/test_mlx_refine.py \
|
||||
fastvideo/tests/mlx/test_mlx_prompt_to_video_decode.py \
|
||||
fastvideo/tests/mlx/test_mlx_wan22_prompt_cache_fingerprint.py \
|
||||
fastvideo/tests/mlx/test_wan22_sample.py \
|
||||
fastvideo/tests/mlx/test_windowed_attention.py \
|
||||
fastvideo/tests/mlx/test_mlx_rife_interpolation.py::test_rife_download_unavailable_has_specific_error \
|
||||
fastvideo/tests/mlx/test_mlx_rife_interpolation.py::test_rife_backend_regression_is_not_skip_eligible \
|
||||
fastvideo/tests/platforms/test_mps_vsa_error.py \
|
||||
-q
|
||||
Reference in New Issue
Block a user