diff --git a/Dockerfile b/Dockerfile index 2e41f58e3887..4011453a4c6b 100644 --- a/Dockerfile +++ b/Dockerfile @@ -14,7 +14,7 @@ # See the License for the specific language governing permissions and # limitations under the License. -ARG BASE_IMAGE=nvcr.io/nvidia/pytorch:22.04-py3 +ARG BASE_IMAGE=nvcr.io/nvidia/pytorch:22.05-py3 # build an image that includes only the nemo dependencies, ensures that dependencies diff --git a/Jenkinsfile b/Jenkinsfile index 5125567884b4..e4f2f47ffea1 100644 --- a/Jenkinsfile +++ b/Jenkinsfile @@ -1,7 +1,7 @@ pipeline { agent { docker { - image 'nvcr.io/nvidia/pytorch:22.04-py3' + image 'nvcr.io/nvidia/pytorch:22.05-py3' args '--device=/dev/nvidia0 --gpus all -e TRANSFORMERS_OFFLINE=1 --user 0:128 -v /home/TestData:/home/TestData -v $HOME/.cache:/root/.cache --shm-size=8g' } } @@ -12,6 +12,12 @@ pipeline { stages { + stage('Add git safe directory'){ + steps{ + sh 'git config --global --add safe.directory /var/lib/jenkins/workspace/NeMo_$GIT_BRANCH' + } + } + stage('nvidia-smi'){ steps{ sh 'nvidia-smi' diff --git a/README.rst b/README.rst index 5696519463cd..f7bb9c05c28d 100644 --- a/README.rst +++ b/README.rst @@ -202,7 +202,7 @@ Megatron GPT training requires NVIDIA Apex to be installed. git clone https://github.com/NVIDIA/apex cd apex - git checkout 9263bc8c6c16555bd55dd759f1a1b8c0cd187d10 + git checkout 5d8c8a8eedaf567d56f0762a45431baf9c0e800e pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" --global-option="--fast_layer_norm" ./ Docker containers: @@ -214,13 +214,13 @@ To build a nemo container with Dockerfile from a branch, please run DOCKER_BUILDKIT=1 docker build -f Dockerfile -t nemo:latest . -If you chose to work with main branch, we recommend using NVIDIA's PyTorch container version 22.04-py3 and then installing from GitHub. +If you chose to work with main branch, we recommend using NVIDIA's PyTorch container version 22.05-py3 and then installing from GitHub. .. code-block:: bash docker run --gpus all -it --rm -v :/NeMo --shm-size=8g \ -p 8888:8888 -p 6006:6006 --ulimit memlock=-1 --ulimit \ - stack=67108864 --device=/dev/snd nvcr.io/nvidia/pytorch:22.04-py3 + stack=67108864 --device=/dev/snd nvcr.io/nvidia/pytorch:22.05-py3 Examples -------- diff --git a/ci.groovy b/ci.groovy index 34ad0dd5dc69..fbb6392ba8a8 100644 --- a/ci.groovy +++ b/ci.groovy @@ -15,7 +15,7 @@ spec: path: /vol/scratch1/scratch.okuchaiev_blossom containers: - name: cuda - image: nvcr.io/nvidia/pytorch:22.04-py3 + image: nvcr.io/nvidia/pytorch:22.05-py3 command: - cat volumeMounts: