Skip to content

Commit

Permalink
Merge branch 'master' into loadams/update-checkout
Browse files Browse the repository at this point in the history
  • Loading branch information
loadams authored Oct 29, 2024
2 parents 5a5c241 + 07cac9e commit 0792334
Show file tree
Hide file tree
Showing 239 changed files with 6,472 additions and 1,345 deletions.
4 changes: 2 additions & 2 deletions .github/workflows/cpu-torch-latest.yml
Original file line number Diff line number Diff line change
Expand Up @@ -50,5 +50,5 @@ jobs:
run: |
unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
cd tests
HF_HOME=/tmp/hf_home/ pytest $PYTEST_OPTS -n 4 unit/ --torch_ver="2.4"
HF_HOME=/tmp/hf_home/ pytest $PYTEST_OPTS -m 'sequential' unit/ --torch_ver="2.4"
HF_HOME=/tmp/hf_home/ pytest $PYTEST_OPTS -n 4 unit/ --torch_ver="2.5"
HF_HOME=/tmp/hf_home/ pytest $PYTEST_OPTS -m 'sequential' unit/ --torch_ver="2.5"
2 changes: 1 addition & 1 deletion .github/workflows/hpu-gaudi2.yml
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ jobs:
# The type of runner that the job will run on
runs-on: [self-hosted, intel, gaudi2]
container:
image: vault.habana.ai/gaudi-docker/1.17.0/ubuntu22.04/habanalabs/pytorch-installer-2.3.1:latest
image: vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.4.0:latest
ports:
- 80
options: --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none --cap-add=sys_nice
Expand Down
46 changes: 46 additions & 0 deletions .github/workflows/no-torch.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,46 @@
name: no-torch

on:
workflow_dispatch:
pull_request:
paths:
- '.github/workflows/no-torch.yml'
- 'op_builder/**'
schedule:
- cron: "0 0 * * *"

concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true

permissions:
contents: read
issues: write

jobs:
unit-tests:
runs-on: ubuntu-22.04

steps:
- uses: actions/checkout@v4

- id: setup-venv
uses: ./.github/workflows/setup-venv

- name: Python environment
run: |
pip uninstall torch --yes
pip list
- name: Build deepspeed
run: |
DS_BUILD_STRING=" " python setup.py sdist
- name: Open GitHub issue if nightly CI fails
if: ${{ failure() && (github.event_name == 'schedule') }}
uses: JasonEtco/create-an-issue@v2
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
with:
filename: .github/ISSUE_TEMPLATE/ci_failure_report.md
update_existing: true
7 changes: 3 additions & 4 deletions .github/workflows/nv-a6000.yml
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ jobs:
unit-tests:
runs-on: [self-hosted, nvidia, a6000]
container:
image: nvcr.io/nvidia/pytorch:23.03-py3
image: nvcr.io/nvidia/pytorch:24.03-py3
ports:
- 80
options: --gpus all --shm-size "8G"
Expand All @@ -47,7 +47,6 @@ jobs:
- name: Install deepspeed
run: |
python -m pip install docutils==0.18.1 jinja2==3.0 urllib3==1.26.11 ninja
python -m pip install pydantic==1.10.11
python -m pip install .[dev,1bit,autotuning,inf]
ds_report
- name: Python environment
Expand All @@ -57,8 +56,8 @@ jobs:
run: |
unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
cd tests
python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2' unit/ --torch_ver="2.0" --cuda_ver="12"
python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2_ops' unit/ --torch_ver="2.0" --cuda_ver="12"
python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2' unit/ --torch_ver="2.3" --cuda_ver="12"
python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2_ops' unit/ --torch_ver="2.3" --cuda_ver="12"
- name: MII unit tests
run: |
BRANCH="main"
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/nv-accelerate-v100.yml
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ concurrency:

jobs:
unit-tests:
runs-on: [self-hosted, nvidia, cu117, v100]
runs-on: [self-hosted, nvidia, cu121, v100]

steps:
- uses: actions/checkout@v4
Expand All @@ -29,7 +29,7 @@ jobs:

- name: Install pytorch
run: |
pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu118
pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
python -c "import torch; print('torch:', torch.__version__, torch)"
python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/nv-ds-chat.yml
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ permissions:

jobs:
unit-tests:
runs-on: [self-hosted, nvidia, cu117, v100]
runs-on: [self-hosted, nvidia, cu121, v100]

steps:
- uses: actions/checkout@v4
Expand All @@ -36,7 +36,7 @@ jobs:

- name: Install pytorch
run: |
pip3 install -U --cache-dir $TORCH_CACHE torch --index-url https://download.pytorch.org/whl/cu118
pip3 install -U --cache-dir $TORCH_CACHE torch --index-url https://download.pytorch.org/whl/cu121
python -c "import torch; print('torch:', torch.__version__, torch)"
python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/nv-human-eval.yml
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ jobs:
unit-tests:
runs-on: [self-hosted, nvidia, a6000]
container:
image: nvcr.io/nvidia/pytorch:23.03-py3
image: nvcr.io/nvidia/pytorch:24.03-py3
ports:
- 80
options: --gpus all --shm-size "8G"
Expand Down Expand Up @@ -50,4 +50,4 @@ jobs:
run: |
unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
cd tests
python -m pytest --color=yes --durations=0 --verbose -rF -m 'evaluation' -k "test_human_eval" unit/ --torch_ver="2.0" --cuda_ver="12"
python -m pytest --color=yes --durations=0 --verbose -rF -m 'evaluation' -k "test_human_eval" unit/ --torch_ver="2.3" --cuda_ver="12"
10 changes: 5 additions & 5 deletions .github/workflows/nv-inference.yml
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ concurrency:

jobs:
unit-tests:
runs-on: [self-hosted, nvidia, cu117, v100]
runs-on: [self-hosted, nvidia, cu121, v100]

steps:
- uses: actions/checkout@v4
Expand All @@ -32,7 +32,7 @@ jobs:

- name: Install pytorch
run: |
pip install -U --cache-dir $TORCH_CACHE torch==2.1.2 torchvision==0.16.2 --index-url https://download.pytorch.org/whl/cu118
pip install -U --cache-dir $TORCH_CACHE torch==2.1.2 torchvision==0.16.2 --index-url https://download.pytorch.org/whl/cu121
python -c "import torch; print('torch:', torch.__version__, torch)"
python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
Expand All @@ -58,8 +58,8 @@ jobs:
run: |
unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
cd tests
#pytest $PYTEST_OPTS -m 'seq_inference' unit/ --torch_ver="2.1" --cuda_ver="11.8"
pytest $PYTEST_OPTS -m 'inference_ops' unit/ --torch_ver="2.1" --cuda_ver="11.8"
pytest $PYTEST_OPTS --forked -n 4 -m 'inference' unit/ --torch_ver="2.1" --cuda_ver="11.8"
#pytest $PYTEST_OPTS -m 'seq_inference' unit/ --torch_ver="2.1" --cuda_ver="12.1"
pytest $PYTEST_OPTS -m 'inference_ops' unit/ --torch_ver="2.1" --cuda_ver="12.1"
pytest $PYTEST_OPTS --forked -n 4 -m 'inference' unit/ --torch_ver="2.1" --cuda_ver="12.1"
# run ds_report again to check updated op list
ds_report
6 changes: 2 additions & 4 deletions .github/workflows/nv-lightning-v100.yml
Original file line number Diff line number Diff line change
Expand Up @@ -19,9 +19,7 @@ concurrency:

jobs:
unit-tests:
runs-on: [self-hosted, nvidia, cu111, v100]

env: {ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true} # Allow using Node16 actions
runs-on: [self-hosted, nvidia, cu121, v100]

steps:
- uses: actions/checkout@v4
Expand All @@ -31,7 +29,7 @@ jobs:

- name: Install pytorch
run: |
pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu118
pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
python -c "import torch; print('torch:', torch.__version__, torch)"
python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/nv-mii.yml
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ concurrency:

jobs:
unit-tests:
runs-on: [self-hosted, nvidia, cu117, v100]
runs-on: [self-hosted, nvidia, cu121, v100]

steps:
- uses: actions/checkout@v4
Expand All @@ -37,7 +37,7 @@ jobs:

- name: Install pytorch
run: |
pip3 install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu118
pip3 install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
python -c "import torch; print('torch:', torch.__version__, torch)"
python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
Expand Down
6 changes: 3 additions & 3 deletions .github/workflows/nv-nightly.yml
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ permissions:

jobs:
unit-tests:
runs-on: [self-hosted, nvidia, cu117, v100]
runs-on: [self-hosted, nvidia, cu121, v100]

steps:
- uses: actions/checkout@v4
Expand All @@ -28,7 +28,7 @@ jobs:

- name: Install pytorch
run: |
pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu118
pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
python -c "import torch; print('torch:', torch.__version__, torch)"
python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
Expand Down Expand Up @@ -58,7 +58,7 @@ jobs:
run: |
unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
cd tests
pytest $PYTEST_OPTS --forked -m 'nightly' unit/ --torch_ver="2.4" --cuda_ver="11.8"
pytest $PYTEST_OPTS --forked -m 'nightly' unit/ --torch_ver="2.5" --cuda_ver="12.1"
- name: Open GitHub issue if nightly CI fails
if: ${{ failure() && (github.event_name == 'schedule') }}
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/nv-sd.yml
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ jobs:
sd-tests:
runs-on: [self-hosted, nvidia, a6000]
container:
image: nvcr.io/nvidia/pytorch:23.03-py3
image: nvcr.io/nvidia/pytorch:24.03-py3
ports:
- 80
options: --gpus all --shm-size "8G"
Expand Down Expand Up @@ -62,7 +62,7 @@ jobs:
run: |
unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
cd tests
python -m pytest --color=yes --durations=0 --verbose -rF -m 'stable_diffusion' -k "TestStableDiffusion" unit/ --torch_ver="2.0" --cuda_ver="12"
python -m pytest --color=yes --durations=0 --verbose -rF -m 'stable_diffusion' -k "TestStableDiffusion" unit/ --torch_ver="2.3" --cuda_ver="12"
- name: Open GitHub issue if weekly CI fails
if: ${{ failure() && (github.event_name == 'schedule') }}
Expand Down
8 changes: 4 additions & 4 deletions .github/workflows/nv-torch-latest-v100.yml
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ concurrency:

jobs:
unit-tests:
runs-on: [self-hosted, nvidia, cu117, v100]
runs-on: [self-hosted, nvidia, cu121, v100]

steps:
- uses: actions/checkout@v4
Expand All @@ -29,7 +29,7 @@ jobs:

- name: Install pytorch
run: |
pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu118
pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121
python -c "import torch; print('torch:', torch.__version__, torch)"
python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
Expand All @@ -55,5 +55,5 @@ jobs:
run: |
unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
cd tests
pytest $PYTEST_OPTS --forked -n 4 unit/ --torch_ver="2.4" --cuda_ver="11.8"
pytest $PYTEST_OPTS --forked -m 'sequential' unit/ --torch_ver="2.4" --cuda_ver="11.8"
pytest $PYTEST_OPTS --forked -n 4 unit/ --torch_ver="2.5" --cuda_ver="12.1"
pytest $PYTEST_OPTS --forked -m 'sequential' unit/ --torch_ver="2.5" --cuda_ver="12.1"
4 changes: 2 additions & 2 deletions .github/workflows/nv-torch-nightly-v100.yml
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ permissions:

jobs:
unit-tests:
runs-on: [self-hosted, nvidia, cu117, v100]
runs-on: [self-hosted, nvidia, cu121, v100]

steps:
- uses: actions/checkout@v4
Expand All @@ -25,7 +25,7 @@ jobs:

- name: Install pytorch
run: |
pip install --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cu118
pip install --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cu121
python -c "import torch; print('torch:', torch.__version__, torch)"
python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/nv-transformers-v100.yml
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ concurrency:

jobs:
unit-tests:
runs-on: [self-hosted, nvidia, cu117, v100]
runs-on: [self-hosted, nvidia, cu121, v100]

steps:
- uses: actions/checkout@v4
Expand All @@ -29,7 +29,7 @@ jobs:
- name: Install pytorch
run: |
# use the same pytorch version as transformers CI
pip install -U --cache-dir $TORCH_CACHE torch==2.0.1+cu118 --index-url https://download.pytorch.org/whl/cu118
pip install -U --cache-dir $TORCH_CACHE torch==2.0.1+cu121 --index-url https://download.pytorch.org/whl/cu121
python -c "import torch; print('torch:', torch.__version__, torch)"
python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
Expand Down
65 changes: 65 additions & 0 deletions .github/workflows/xpu-compile.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,65 @@
name: xpu-compile

on:
workflow_dispatch:
schedule:
- cron: "0 0 * * *"
pull_request:
paths:
- ".github/workflows/xpu-compile.yml"

concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true

permissions:
contents: read
issues: write

jobs:
compile-tests:
runs-on: [self-hosted, intel, xpu]
container:
image: intel/oneapi-basekit:2024.2.1-0-devel-ubuntu22.04
ports:
- 80
options: --privileged -it --rm --device /dev/dri:/dev/dri -v /dev/dri/by-path:/dev/dri/by-path --ipc=host --cap-add=ALL

steps:
- uses: actions/checkout@v4
- name: Install prerequisite
run: |
apt-get update
apt-get install clinfo libaio-dev python3-pip -y
pip install torch==2.3.1 -f https://pytorch-extension.intel.com/release-whl/stable/xpu/us/torch/
pip install intel-extension-for-pytorch==2.3.110+xpu -f https://pytorch-extension.intel.com/release-whl/stable/xpu/us/intel-extension-for-pytorch/
pip install oneccl_bind_pt==2.3.100+xpu -f https://pytorch-extension.intel.com/release-whl/stable/xpu/us/oneccl-bind-pt/
pip install torchvision==0.18.1 -f https://pytorch-extension.intel.com/release-whl/stable/xpu/us/torchvision/
pip install https://github.com/intel/intel-xpu-backend-for-triton/releases/download/v3.0.0b2/triton_xpu-3.0.0b2-cp310-cp310-linux_x86_64.whl
pip install py-cpuinfo numpy
pip install .[dev,autotuning]
- name: Check container state
run: |
ldd --version
ds_report
python3 -c "import torch; print('torch:', torch.__version__, torch)"
python3 -c "import torch; import intel_extension_for_pytorch; print('XPU available:', torch.xpu.is_available())"
python3 -c "from deepspeed.accelerator import get_accelerator; print('accelerator:', get_accelerator()._name)"
pip list
- name: Compile Status
shell: bash
run: |
echo "# torch.compile graph breaks" >> $GITHUB_STEP_SUMMARY
export FI_HMEM=system
ulimit -n 1048575
cd tests/torch_compile
export ZE_AFFINITY_MASK=0,1
echo "## ZeRO stage 3" >> $GITHUB_STEP_SUMMARY
deepspeed test_compile.py --deepspeed_config ds_config_z3.json 2>&1 | tee log_z3.txt
# for each line start with 'dynamo_output', extract the second field and following fields and append to GITHUB_STEP_SUMMARY using awk
cat log_z3.txt | awk '/^dynamo_output/ {$1=""; print $0}' >> $GITHUB_STEP_SUMMARY
echo "## ZeRO stage 2" >> $GITHUB_STEP_SUMMARY
deepspeed test_compile.py --deepspeed_config ds_config_z2.json 2>&1 | tee log_z2.txt
cat log_z2.txt | awk '/^dynamo_output/ {$1=""; print $0}' >> $GITHUB_STEP_SUMMARY
Loading

0 comments on commit 0792334

Please sign in to comment.