Update 3 docker files to use cu118 (#23406)
* fix --------- Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
20
.github/workflows/build-docker-images.yml
vendored
20
.github/workflows/build-docker-images.yml
vendored
@@ -71,6 +71,16 @@ jobs:
|
|||||||
name: "Latest PyTorch + DeepSpeed"
|
name: "Latest PyTorch + DeepSpeed"
|
||||||
runs-on: ubuntu-latest
|
runs-on: ubuntu-latest
|
||||||
steps:
|
steps:
|
||||||
|
- name: Cleanup disk
|
||||||
|
run: |
|
||||||
|
sudo ls -l /usr/local/lib/
|
||||||
|
sudo ls -l /usr/share/
|
||||||
|
sudo du -sh /usr/local/lib/
|
||||||
|
sudo du -sh /usr/share/
|
||||||
|
sudo rm -rf /usr/local/lib/android
|
||||||
|
sudo rm -rf /usr/share/dotnet
|
||||||
|
sudo du -sh /usr/local/lib/
|
||||||
|
sudo du -sh /usr/share/
|
||||||
-
|
-
|
||||||
name: Set up Docker Buildx
|
name: Set up Docker Buildx
|
||||||
uses: docker/setup-buildx-action@v2
|
uses: docker/setup-buildx-action@v2
|
||||||
@@ -98,6 +108,16 @@ jobs:
|
|||||||
name: "Latest PyTorch + DeepSpeed (Push CI - Daily Build)"
|
name: "Latest PyTorch + DeepSpeed (Push CI - Daily Build)"
|
||||||
runs-on: ubuntu-latest
|
runs-on: ubuntu-latest
|
||||||
steps:
|
steps:
|
||||||
|
- name: Cleanup disk
|
||||||
|
run: |
|
||||||
|
sudo ls -l /usr/local/lib/
|
||||||
|
sudo ls -l /usr/share/
|
||||||
|
sudo du -sh /usr/local/lib/
|
||||||
|
sudo du -sh /usr/share/
|
||||||
|
sudo rm -rf /usr/local/lib/android
|
||||||
|
sudo rm -rf /usr/share/dotnet
|
||||||
|
sudo du -sh /usr/local/lib/
|
||||||
|
sudo du -sh /usr/share/
|
||||||
-
|
-
|
||||||
name: Set up Docker Buildx
|
name: Set up Docker Buildx
|
||||||
uses: docker/setup-buildx-action@v2
|
uses: docker/setup-buildx-action@v2
|
||||||
|
|||||||
@@ -35,7 +35,7 @@ RUN [ "$PYTORCH" != "pre" ] && python3 -m pip install --no-cache-dir -U $VERSION
|
|||||||
RUN python3 -m pip install --no-cache-dir -U tensorflow==2.12 protobuf==3.20.3 tensorflow_text tensorflow_probability
|
RUN python3 -m pip install --no-cache-dir -U tensorflow==2.12 protobuf==3.20.3 tensorflow_text tensorflow_probability
|
||||||
RUN python3 -m pip uninstall -y flax jax
|
RUN python3 -m pip uninstall -y flax jax
|
||||||
|
|
||||||
RUN python3 -m pip install --no-cache-dir intel_extension_for_pytorch==$INTEL_TORCH_EXT+cpu -f https://software.intel.com/ipex-whl-stable
|
RUN python3 -m pip install --no-cache-dir intel_extension_for_pytorch==$INTEL_TORCH_EXT+cpu -f https://developer.intel.com/ipex-whl-stable-cpu
|
||||||
|
|
||||||
RUN python3 -m pip install --no-cache-dir git+https://github.com/facebookresearch/detectron2.git pytesseract
|
RUN python3 -m pip install --no-cache-dir git+https://github.com/facebookresearch/detectron2.git pytesseract
|
||||||
RUN python3 -m pip install -U "itsdangerous<2.1.0"
|
RUN python3 -m pip install -U "itsdangerous<2.1.0"
|
||||||
|
|||||||
@@ -1,12 +1,12 @@
|
|||||||
# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel_22-08.html#rel_22-08
|
# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel_22-08.html#rel_22-08
|
||||||
FROM nvcr.io/nvidia/pytorch:22.08-py3
|
FROM nvcr.io/nvidia/pytorch:22.12-py3
|
||||||
LABEL maintainer="Hugging Face"
|
LABEL maintainer="Hugging Face"
|
||||||
|
|
||||||
ARG DEBIAN_FRONTEND=noninteractive
|
ARG DEBIAN_FRONTEND=noninteractive
|
||||||
|
|
||||||
ARG PYTORCH='2.0.1'
|
ARG PYTORCH='2.0.1'
|
||||||
# Example: `cu102`, `cu113`, etc.
|
# Example: `cu102`, `cu113`, etc.
|
||||||
ARG CUDA='cu117'
|
ARG CUDA='cu118'
|
||||||
|
|
||||||
RUN apt -y update
|
RUN apt -y update
|
||||||
RUN apt install -y libaio-dev
|
RUN apt install -y libaio-dev
|
||||||
@@ -15,6 +15,8 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip
|
|||||||
ARG REF=main
|
ARG REF=main
|
||||||
RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
|
RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
|
||||||
|
|
||||||
|
RUN python3 -m pip uninstall -y torch torchvision torchaudio
|
||||||
|
|
||||||
# Install latest release PyTorch
|
# Install latest release PyTorch
|
||||||
# (PyTorch must be installed before pre-compiling any DeepSpeed c++/cuda ops.)
|
# (PyTorch must be installed before pre-compiling any DeepSpeed c++/cuda ops.)
|
||||||
# (https://www.deepspeed.ai/tutorials/advanced-install/#pre-install-deepspeed-ops)
|
# (https://www.deepspeed.ai/tutorials/advanced-install/#pre-install-deepspeed-ops)
|
||||||
|
|||||||
@@ -1,11 +1,11 @@
|
|||||||
# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel_22-08.html#rel_22-08
|
# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel_22-08.html#rel_22-08
|
||||||
FROM nvcr.io/nvidia/pytorch:22.08-py3
|
FROM nvcr.io/nvidia/pytorch:22.12-py3
|
||||||
LABEL maintainer="Hugging Face"
|
LABEL maintainer="Hugging Face"
|
||||||
|
|
||||||
ARG DEBIAN_FRONTEND=noninteractive
|
ARG DEBIAN_FRONTEND=noninteractive
|
||||||
|
|
||||||
# Example: `cu102`, `cu113`, etc.
|
# Example: `cu102`, `cu113`, etc.
|
||||||
ARG CUDA='cu117'
|
ARG CUDA='cu118'
|
||||||
|
|
||||||
RUN apt -y update
|
RUN apt -y update
|
||||||
RUN apt install -y libaio-dev
|
RUN apt install -y libaio-dev
|
||||||
@@ -14,6 +14,8 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip
|
|||||||
ARG REF=main
|
ARG REF=main
|
||||||
RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
|
RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
|
||||||
|
|
||||||
|
RUN python3 -m pip uninstall -y torch torchvision torchaudio
|
||||||
|
|
||||||
# Install **nightly** release PyTorch (flag `--pre`)
|
# Install **nightly** release PyTorch (flag `--pre`)
|
||||||
# (PyTorch must be installed before pre-compiling any DeepSpeed c++/cuda ops.)
|
# (PyTorch must be installed before pre-compiling any DeepSpeed c++/cuda ops.)
|
||||||
# (https://www.deepspeed.ai/tutorials/advanced-install/#pre-install-deepspeed-ops)
|
# (https://www.deepspeed.ai/tutorials/advanced-install/#pre-install-deepspeed-ops)
|
||||||
|
|||||||
@@ -1,4 +1,4 @@
|
|||||||
FROM nvidia/cuda:11.7.1-cudnn8-devel-ubuntu20.04
|
FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu20.04
|
||||||
LABEL maintainer="Hugging Face"
|
LABEL maintainer="Hugging Face"
|
||||||
|
|
||||||
ARG DEBIAN_FRONTEND=noninteractive
|
ARG DEBIAN_FRONTEND=noninteractive
|
||||||
@@ -16,7 +16,7 @@ ARG PYTORCH='2.0.1'
|
|||||||
ARG TORCH_VISION=''
|
ARG TORCH_VISION=''
|
||||||
ARG TORCH_AUDIO=''
|
ARG TORCH_AUDIO=''
|
||||||
# Example: `cu102`, `cu113`, etc.
|
# Example: `cu102`, `cu113`, etc.
|
||||||
ARG CUDA='cu117'
|
ARG CUDA='cu118'
|
||||||
|
|
||||||
RUN [ ${#PYTORCH} -gt 0 ] && VERSION='torch=='$PYTORCH'.*' || VERSION='torch'; python3 -m pip install --no-cache-dir -U $VERSION --extra-index-url https://download.pytorch.org/whl/$CUDA
|
RUN [ ${#PYTORCH} -gt 0 ] && VERSION='torch=='$PYTORCH'.*' || VERSION='torch'; python3 -m pip install --no-cache-dir -U $VERSION --extra-index-url https://download.pytorch.org/whl/$CUDA
|
||||||
RUN [ ${#TORCH_VISION} -gt 0 ] && VERSION='torchvision=='TORCH_VISION'.*' || VERSION='torchvision'; python3 -m pip install --no-cache-dir -U $VERSION --extra-index-url https://download.pytorch.org/whl/$CUDA
|
RUN [ ${#TORCH_VISION} -gt 0 ] && VERSION='torchvision=='TORCH_VISION'.*' || VERSION='torchvision'; python3 -m pip install --no-cache-dir -U $VERSION --extra-index-url https://download.pytorch.org/whl/$CUDA
|
||||||
|
|||||||
Reference in New Issue
Block a user