Gaudi RHOAI notebook image 1.19.0 update

enterprise/redhat/openshift-ai/gaudi/README.md

@@ -6,9 +6,10 @@ Intel® Gaudi AI Software Tools for OpenShift AI(RedHat OpenShift Data Science/R
 
 | Notebook Container Name | Tools | Image Name |
 | -----------------------------| ------------- | ------------- |
-| Intel Gaudi Notebook Container 1.17.0-495 | [Intel® Gaudi Software Stack*](https://docs.habana.ai/en/latest/Installation_Guide/Bare_Metal_Fresh_OS.html), [Intel® Gaudi PyTorch](https://docs.habana.ai/en/latest/PyTorch/index.html), [Intel® Gaudi vLLM](https://github.com/HabanaAI/vllm-fork.git), [Intel® Gaudi DeepSpeed](https://github.com/HabanaAI/DeepSpeed) | [`registry.connect.redhat.com/intel/gaudi-notebooks:1.17.0-495-rhel-9.2`](registry.connect.redhat.com/intel/gaudi-notebooks@sha256:a62baf968caa7dd23b7f4cdcddc26e109d894f1436e247b4ea1e2fb4a5c94d54) |
-| Intel Gaudi Notebook Container 1.17.1-40 | [Intel® Gaudi Software Stack*](https://docs.habana.ai/en/latest/Installation_Guide/Bare_Metal_Fresh_OS.html), [Intel® Gaudi PyTorch](https://docs.habana.ai/en/latest/PyTorch/index.html), [Intel® Gaudi vLLM](https://github.com/HabanaAI/vllm-fork.git), [Intel® Gaudi DeepSpeed](https://github.com/HabanaAI/DeepSpeed) | [`registry.connect.redhat.com/intel/gaudi-notebooks:1.17.1-40-rhel-9.2`](registry.connect.redhat.com/intel/gaudi-notebooks@sha256:00ca535956b7fcdd91e71bc4a3cd4493ddcaceea9b8d7bb95a7edc0e1cb0bac4) |
-| Intel Gaudi Notebook Container 1.18.0-524 | [Intel® Gaudi Software Stack*](https://docs.habana.ai/en/latest/Installation_Guide/Bare_Metal_Fresh_OS.html), [Intel® Gaudi PyTorch](https://docs.habana.ai/en/latest/PyTorch/index.html), [Intel® Gaudi vLLM](https://github.com/HabanaAI/vllm-fork.git), [Intel® Gaudi DeepSpeed](https://github.com/HabanaAI/DeepSpeed) | [`registry.connect.redhat.com/intel/gaudi-notebooks:1.18.0-524-rhel-9.2`](registry.connect.redhat.com/intel/gaudi-notebooks@sha256:142b11253e5708ff9744c895868b2adda2f6f01c40127b71f1aca3d7a6e6bc29) |
+| Intel Gaudi Notebook Container 1.19.0-561 | [Intel® Gaudi Software Stack*](https://docs.habana.ai/en/latest/Installation_Guide/Bare_Metal_Fresh_OS.html), [Intel® Gaudi PyTorch](https://docs.habana.ai/en/latest/PyTorch/index.html), [Intel® Gaudi vLLM](https://github.com/HabanaAI/vllm-fork.git), [Intel® Gaudi DeepSpeed](https://github.com/HabanaAI/DeepSpeed) | [`registry.connect.redhat.com/intel/gaudi-notebooks:1.19.0-561-rhel-9.4`](https://catalog.redhat.com/software/containers/66e2072057f53c17d73d67e1?architecture=amd64&tag=1.18.0-524-rhel-9.2&image=676b2fd90e7869ebe618b78b&gti-tabs=registry-tokens), [`registry.connect.redhat.com/intel/gaudi-notebooks:1.19.0-561-rhel-9.2`](https://catalog.redhat.com/software/containers/66e2072057f53c17d73d67e1?architecture=amd64&tag=1.18.0-524-rhel-9.2&image=676b32a224dabcac4cf84cb3&gti-tabs=registry-tokens) |
+| Intel Gaudi Notebook Container 1.18.0-524 | [Intel® Gaudi Software Stack*](https://docs.habana.ai/en/latest/Installation_Guide/Bare_Metal_Fresh_OS.html), [Intel® Gaudi PyTorch](https://docs.habana.ai/en/latest/PyTorch/index.html), [Intel® Gaudi vLLM](https://github.com/HabanaAI/vllm-fork.git), [Intel® Gaudi DeepSpeed](https://github.com/HabanaAI/DeepSpeed) | [`registry.connect.redhat.com/intel/gaudi-notebooks:1.18.0-524-rhel-9.2`](https://catalog.redhat.com/software/containers/66e2072057f53c17d73d67e1?architecture=amd64&tag=1.18.0-524-rhel-9.2&image=67181ccca33f4e501721789f&gti-tabs=registry-tokens) |
+| Intel Gaudi Notebook Container 1.17.1-40 | [Intel® Gaudi Software Stack*](https://docs.habana.ai/en/latest/Installation_Guide/Bare_Metal_Fresh_OS.html), [Intel® Gaudi PyTorch](https://docs.habana.ai/en/latest/PyTorch/index.html), [Intel® Gaudi vLLM](https://github.com/HabanaAI/vllm-fork.git), [Intel® Gaudi DeepSpeed](https://github.com/HabanaAI/DeepSpeed) | [`registry.connect.redhat.com/intel/gaudi-notebooks:1.17.1-40-rhel-9.2`](https://catalog.redhat.com/software/containers/66e2072057f53c17d73d67e1?architecture=amd64&tag=1.18.0-524-rhel-9.2&image=66fc3bf38081186cfc015a0d&gti-tabs=registry-tokens) |
+| Intel Gaudi Notebook Container 1.17.0-495 | [Intel® Gaudi Software Stack*](https://docs.habana.ai/en/latest/Installation_Guide/Bare_Metal_Fresh_OS.html), [Intel® Gaudi PyTorch](https://docs.habana.ai/en/latest/PyTorch/index.html), [Intel® Gaudi vLLM](https://github.com/HabanaAI/vllm-fork.git), [Intel® Gaudi DeepSpeed](https://github.com/HabanaAI/DeepSpeed) | [`registry.connect.redhat.com/intel/gaudi-notebooks:1.17.0-495-rhel-9.2`](https://catalog.redhat.com/software/containers/66e2072057f53c17d73d67e1?architecture=amd64&tag=1.18.0-524-rhel-9.2&image=66e0ac59261d52855750518c&gti-tabs=registry-tokens) |
 
 ## Run Gaudi Notebook Containers
 

enterprise/redhat/openshift-ai/gaudi/crd-sample.yaml

@@ -16,7 +16,7 @@ apiVersion: aitools.intel/v1
 kind: GaudiAIToolsContainer
 metadata:
   labels:
-    gaudi-software-version: '1.17.1-40'
+    gaudi-software-version: '1.19.0-561'
   name: intel-gaudi
 spec:
   nameOverride: ""
@@ -25,6 +25,8 @@ spec:
     registry: registry.connect.redhat.com
     repo: intel/gaudi-notebooks
     tags:
-      - gaudi_software: "1.17.1-40"
+      - gaudi_software: "1.19.0-561"
         rhel_os: "9.2"
+      - gaudi_software: "1.19.0-561"
+        rhel_os: "9.4"
   namespace: redhat-ods-applications

enterprise/redhat/openshift-ai/gaudi/docker/Dockerfile.rhel9.2

@@ -69,6 +69,7 @@ RUN mkdir -p /licenses && \
 ENV PYTHON_VERSION=3.10
 COPY install-python310.sh .
 RUN ./install-python310.sh rhel9.2 && rm install-python310.sh
+RUN echo "/usr/local/lib" > /etc/ld.so.conf.d/python.conf && ldconfig
 ENV LD_LIBRARY_PATH=/usr/local/lib:$LD_LIBRARY_PATH
 
 COPY install_efa.sh .
@@ -194,17 +195,11 @@ RUN dnf install --allowerasing -y \
     gperftools-devel && \
     dnf clean all && rm -rf /var/cache/yum
 
-RUN dnf config-manager --add-repo https://yum.repos.intel.com/mkl/setup/intel-mkl.repo -y && \
-    dnf install --allowerasing -y intel-mkl-64bit-2020.4-912 && \
-    dnf clean all && rm -rf /var/cache/yum
-
 # Set LD_PRELOAD after all required installations to
 # avoid warnings during docker creation
 ENV LD_PRELOAD=/lib64/libtcmalloc.so.4
 ENV TCMALLOC_LARGE_ALLOC_REPORT_THRESHOLD=7516192768
 
-RUN rm -rf /tmp/*
-
 USER 1001
 
 COPY --chown=1001:0 install_packages.sh .
@@ -238,9 +233,10 @@ RUN python -m pip install -r requirements.txt && \
 RUN cd ${APP_ROOT}/ && \
     git clone https://github.com/HabanaAI/vllm-fork.git && \
     cd vllm-fork && \
-    VLLM_TARGET_DEVICE=hpu pip install -e .
+    git checkout habana_main && \
+    pip install -r requirements-hpu.txt && \
+    VLLM_TARGET_DEVICE=hpu python setup.py develop
 
 WORKDIR ${APP_ROOT}/src
 ENV NOTEBOOK_SAMPLES_LINK="https://raw.githubusercontent.com/intel/ai-containers/refs/heads/main/enterprise/redhat/openshift-ai/gaudi/demo/oneapi-sample.ipynb"
-
 ENTRYPOINT ["bash", "-c", "/opt/app-root/builder/run"]

enterprise/redhat/openshift-ai/gaudi/docker/Dockerfile.rhel9.4

@@ -29,10 +29,15 @@ RUN echo "[CRB]" > /etc/yum.repos.d/CentOS-Linux-CRB.repo && \
     echo "gpgkey=https://www.centos.org/keys/RPM-GPG-KEY-CentOS-Official-SHA256" >> /etc/yum.repos.d/CentOS-Linux-CRB.repo && \
     echo "gpgcheck=1" >> /etc/yum.repos.d/CentOS-Linux-CRB.repo
 
-RUN dnf install -y https://dl.fedoraproject.org/pub/epel/epel-release-latest-9.noarch.rpm && \
-    dnf clean all && rm -rf /var/cache/yum
-
 RUN dnf install -y \
+        python3-dnf-plugin-versionlock && \
+    dnf versionlock add redhat-release* && \
+    dnf clean all
+
+RUN dnf update -y && dnf install -y https://dl.fedoraproject.org/pub/epel/epel-release-latest-9.noarch.rpm && \
+    dnf clean all
+
+RUN dnf update -y && dnf install -y \
     clang \
     cmake3 \
     cpp \
@@ -49,8 +54,8 @@ RUN dnf install -y \
     lsof \
     python3-devel \
     openssh-clients \
-    openssl-1:3.0.7-28.el9_4 \
-    openssl-devel-1:3.0.7-28.el9_4 \
+    openssl \
+    openssl-devel \
     libjpeg-devel \
     openssh-server \
     lsb_release \
@@ -66,24 +71,15 @@ RUN dnf install -y \
     python3.11-pip \
     python3.11-devel \
     python3.11-rpm \
-    ffmpeg-free \
-    python3-dnf-plugin-versionlock && \
+    ffmpeg-free && \
     # update pkgs (except OS version) for resolving potentials CVEs
-    dnf versionlock add redhat-release* openssl* libcurl-minimal curl-minimal ima-evm-utils python3-rpm rpm* && \
-    dnf update -y && \
+    dnf versionlock add python3-rpm rpm* && \
     dnf clean all && rm -rf /var/cache/yum && \
     rm -f /etc/ssh/ssh_host_*_key*
 
 RUN mkdir -p /licenses && \
     wget -O /licenses/LICENSE https://raw.githubusercontent.com/intel/ai-containers/main/LICENSE
 
-RUN alternatives --install /usr/bin/python3 python3 /usr/bin/python3.11 2 && \
-    alternatives --install /usr/bin/python3 python3 /usr/bin/python3.9 1 && \
-    alternatives --set python3 /usr/bin/python3.11 && \
-    alternatives --install /usr/bin/pip3 pip3 /usr/bin/pip3.11 2 && \
-    alternatives --install /usr/bin/pip3 pip3 /usr/bin/pip3.9 1 && \
-    alternatives --set pip3 /usr/bin/pip3.11
-
 COPY install_efa.sh .
 RUN ./install_efa.sh && rm install_efa.sh && rm -rf /etc/ld.so.conf.d/efa.conf /etc/profile.d/efa.sh
 
@@ -193,32 +189,18 @@ RUN echo "[CRB]" > /etc/yum.repos.d/CentOS-Linux-CRB.repo && \
     echo "gpgkey=https://www.centos.org/keys/RPM-GPG-KEY-CentOS-Official-SHA256" >> /etc/yum.repos.d/CentOS-Linux-CRB.repo && \
     echo "gpgcheck=1" >> /etc/yum.repos.d/CentOS-Linux-CRB.repo
 
-RUN dnf install --allowerasing -y \
-    curl-7.76.1-29.el9_4.1 \
-    cairo-devel \
-    numactl-devel \
-    iproute \
-    which \
-    zlib-devel \
-    lapack-devel \
-    openblas-devel \
-    numactl \
-    gperftools-devel && \
-    dnf clean all && rm -rf /var/cache/yum
-
-RUN echo "[oneAPI]" >> /etc/yum.repos.d/oneAPI.repo && \
-    echo "name=Intel® oneAPI repository" >> /etc/yum.repos.d/oneAPI.repo && \
-    echo "baseurl=https://yum.repos.intel.com/oneapi" >> /etc/yum.repos.d/oneAPI.repo && \
-    echo 'enabled=1'  >> /etc/yum.repos.d/oneAPI.repo && \
-    echo "gpgcheck=1" >> /etc/yum.repos.d/oneAPI.repo && \
-    echo "repo_gpgcheck=1" >> /etc/yum.repos.d/oneAPI.repo && \
-    echo "gpgkey=https://yum.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB" >> /etc/yum.repos.d/oneAPI.repo
-
-RUN dnf install --allowerasing -y intel-oneapi-mkl-2024.2.0 && \
+RUN dnf update -y && dnf install --nodocs --setopt=install_weak_deps=false --allowerasing -y \
+        cairo-devel \
+        numactl-devel \
+        iproute \
+        which \
+        zlib-devel \
+        lapack-devel \
+        openblas-devel \
+        numactl \
+        gperftools-devel && \
     dnf clean all && rm -rf /var/cache/yum
 
-ENV LD_LIBRARY_PATH=/opt/intel/oneapi/mkl/2024.2/lib:${LD_LIBRARY_PATH}
-
 RUN rm -rf /tmp/*
 
 USER 1001
@@ -260,9 +242,11 @@ RUN python -m pip install -r requirements.txt && \
 RUN cd ${APP_ROOT}/ && \
     git clone https://github.com/HabanaAI/vllm-fork.git && \
     cd vllm-fork && \
-    VLLM_TARGET_DEVICE=hpu pip install -e .
+    git checkout habana_main && \
+    pip install -r requirements-hpu.txt && \
+    VLLM_TARGET_DEVICE=hpu python setup.py develop
 
 WORKDIR ${APP_ROOT}/src
-ENV JUPYTER_PRELOAD_REPOS="https://github.com/IntelAI/oneAPI-samples"
-ENV REPO_BRANCH="main"
+ENV NOTEBOOK_SAMPLES_LINK="https://raw.githubusercontent.com/intel/ai-containers/refs/heads/main/enterprise/redhat/openshift-ai/gaudi/demo/oneapi-sample.ipynb"
+
 ENTRYPOINT ["bash", "-c", "/opt/app-root/builder/run"]

enterprise/redhat/openshift-ai/gaudi/docker/docker-compose.yaml

@@ -22,12 +22,12 @@ services:
         https_proxy: ${https_proxy}
         no_proxy: ""
         ARTIFACTORY_URL: ${ARTIFACTORY_URL:-vault.habana.ai}
-        VERSION: ${VERSION:-1.18.0}
-        REVISION: ${REVISION:-524}
+        VERSION: ${VERSION:-1.19.0}
+        REVISION: ${REVISION:-561}
       context: .
       target: gaudi-base
       dockerfile: Dockerfile.rhel${RHEL_OS:-9.2}
-    image: ${REGISTRY}/${REPO}:b-${GITHUB_RUN_NUMBER:-0}-gaudi-base-${VERSION:-1.18.0}-${REVISION:-524}-rhel-${RHEL_OS:-9.2}
+    image: ${REGISTRY}/${REPO}:b-${GITHUB_RUN_NUMBER:-0}-gaudi-base-${VERSION:-1.19.0}-${REVISION:-561}-rhel-${RHEL_OS:-9.2}
     entrypoint: ["/bin/bash", "-c"]
     command: >
       "hl-smi"
@@ -37,17 +37,17 @@ services:
         BASE_IMAGE: ${BASE_IMAGE:-registry.access.redhat.com/ubi9/ubi}
         BASE_TAG: ${RHEL_OS:-9.2}
         BASE_NAME: rhel${RHEL_OS:-rhel9.2}
-        PT_VERSION: ${PT_VERSION:-2.4.0}
+        PT_VERSION: ${PT_VERSION:-2.5.1}
         http_proxy: ${http_proxy}
         https_proxy: ${https_proxy}
         no_proxy: ""
         ARTIFACTORY_URL: ${ARTIFACTORY_URL:-vault.habana.ai}
-        VERSION: ${VERSION:-1.18.0}
-        REVISION: ${REVISION:-524}
+        VERSION: ${VERSION:-1.19.0}
+        REVISION: ${REVISION:-561}
       context: .
       target: gaudi-pytorch
       dockerfile: Dockerfile.rhel${RHEL_OS:-9.2}
-    image: ${REGISTRY}/${REPO}:b-${GITHUB_RUN_NUMBER:-0}-gaudi-pytorch-${VERSION:-1.18.0}-${REVISION:-524}-rhel-${RHEL_OS:-9.2}
+    image: ${REGISTRY}/${REPO}:b-${GITHUB_RUN_NUMBER:-0}-gaudi-pytorch-${VERSION:-1.19.0}-${REVISION:-561}-rhel-${RHEL_OS:-9.2}
     entrypoint: ["/bin/bash", "-c"]
     command: >
       "python -c 'import torch'"
@@ -57,17 +57,17 @@ services:
         BASE_IMAGE: ${BASE_IMAGE:-registry.access.redhat.com/ubi9/ubi}
         BASE_TAG: ${RHEL_OS:-9.2}
         BASE_NAME: ${BASE_NAME:-rhel9.2}
-        PT_VERSION: ${PT_VERSION:-2.4.0}
+        PT_VERSION: ${PT_VERSION:-2.5.1}
         http_proxy: ${http_proxy}
         https_proxy: ${https_proxy}
         no_proxy: ""
         ARTIFACTORY_URL: ${ARTIFACTORY_URL:-vault.habana.ai}
-        VERSION: ${VERSION:-1.18.0}
-        REVISION: ${REVISION:-524}
+        VERSION: ${VERSION:-1.19.0}
+        REVISION: ${REVISION:-561}
       context: .
       target: gaudi-notebooks
       dockerfile: Dockerfile.rhel${RHEL_OS:-9.2}
-    image: ${REGISTRY}/${REPO}:b-${GITHUB_RUN_NUMBER:-0}-gaudi-notebook-${VERSION:-1.18.0}-${REVISION:-524}-rhel-${RHEL_OS:-9.2}
+    image: ${REGISTRY}/${REPO}:b-${GITHUB_RUN_NUMBER:-0}-gaudi-notebook-${VERSION:-1.19.0}-${REVISION:-561}-rhel-${RHEL_OS:-9.2}
     entrypoint: ["/bin/bash", "-c"]
     command: >
       "python -m jupyter notebook --version"

enterprise/redhat/openshift-ai/gaudi/docker/install-python310.sh

@@ -24,12 +24,12 @@ case "${_BASE_NAME}" in
 	echo "Skip install Python3.10 from source on Ubuntu22.04"
 	exit 0
 	;;
-*debian* | *ubuntu*)
+*ubuntu*)
 	apt update
 	apt install -y libsqlite3-dev libreadline-dev
 	;;
 *rhel*)
-	yum install -y sqlite-devel readline-devel xz-devel
+	dnf install -y sqlite-devel readline-devel xz-devel
 	;;
 *tencentos3.1*)
 	dnf install -y sqlite-devel readline-devel zlib-devel xz-devel bzip2-devel libffi-devel
@@ -42,21 +42,6 @@ case "${_BASE_NAME}" in
 		make && make install
 	ln -s /etc/pki/tls/cert.pem /usr/local/openssl-1.1.1w/ssl/cert.pem
 
-	PATH=$PATH:/usr/local/protoc/bin:/usr/local/openssl-1.1.1w/bin
-	LD_LIBRARY_PATH=/usr/local/openssl-1.1.1w/lib:$LD_LIBRARY_PATH
-	_SSL_LIB="--with-openssl=/usr/local/openssl-1.1.1w"
-	;;
-*amzn2*)
-	yum install -y sqlite-devel readline-devel
-	wget -nv -O /opt/openssl-1.1.1w.tar.gz https://github.com/openssl/openssl/releases/download/OpenSSL_1_1_1w/openssl-1.1.1w.tar.gz &&
-		cd /opt/ &&
-		tar xzf openssl-1.1.1w.tar.gz &&
-		rm -rf openssl-1.1.1w.tar.gz &&
-		cd openssl-1.1.1w &&
-		./config --prefix=/usr/local/openssl-1.1.1w shared zlib &&
-		make && make install
-	ln -s /etc/pki/tls/cert.pem /usr/local/openssl-1.1.1w/ssl/cert.pem
-
 	PATH=$PATH:/usr/local/protoc/bin:/usr/local/openssl-1.1.1w/bin
 	LD_LIBRARY_PATH=/usr/local/openssl-1.1.1w/lib:$LD_LIBRARY_PATH
 	_SSL_LIB="--with-openssl=/usr/local/openssl-1.1.1w"
@@ -75,9 +60,6 @@ make -j && make altinstall
 # post install
 case "${_BASE_NAME}" in
 *rhel9*)
-	alternatives --install /usr/bin/python3 python3 /usr/local/bin/python3.10 2 &&
-		alternatives --install /usr/bin/python3 python3 /usr/bin/python3.9 1 &&
-		alternatives --set python3 /usr/local/bin/python3.10
 	export LD_LIBRARY_PATH=/usr/local/lib:$LD_LIBRARY_PATH
 	;;
 *tencentos3.1*)
@@ -88,16 +70,6 @@ case "${_BASE_NAME}" in
 		alternatives --set python3 /usr/local/bin/python3.10
 	export LD_LIBRARY_PATH=/usr/local/lib:$LD_LIBRARY_PATH
 	;;
-*amzn2*)
-	update-alternatives --install /usr/bin/python3 python3 /usr/local/bin/python3.10 3 &&
-		update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.8 2 &&
-		update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.7 1
-	;;
-*debian*)
-	update-alternatives --install /usr/bin/python3 python3 /usr/local/bin/python3.10 3
-	update-alternatives --install /usr/bin/python3 python3 /usr/local/bin/python3.8 2
-	update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.7 1
-	;;
 esac
 
 python3 -m pip install --upgrade pip setuptools

enterprise/redhat/openshift-ai/gaudi/docker/install_packages.sh

@@ -27,9 +27,6 @@ case "${BASE_NAME}" in
 *rhel8*)
 	os_string="rhel86"
 	;;
-*amzn2*)
-	os_string="amzn2"
-	;;
 *tencentos*)
 	os_string="tencentos31"
 	;;

enterprise/redhat/openshift-ai/gaudi/docker/requirements.txt

@@ -1,5 +1,5 @@
 # LLM Packages
-deepspeed @ git+https://github.com/HabanaAI/DeepSpeed.git@1.17.1
+deepspeed @ git+https://github.com/HabanaAI/DeepSpeed.git@1.19.0
 
 # Datascience and useful extensions
 kafka-python~=2.0.2