Merge branch 'main' into workflow-traces-update

containers · Jul 11, 2024 · 9389041 · 9389041
2 parents f290233 + 241e0e4
commit 9389041
Show file tree

Hide file tree

Showing 3 changed files with 21 additions and 13 deletions.
diff --git a/recipes/computer_vision/object_detection/README.md b/recipes/computer_vision/object_detection/README.md
@@ -56,7 +56,7 @@ The local Model Service relies on a volume mount to the localhost to access the
 make run
 ```
 
-As stated above, by default the model service will use [`facebook/detr-resnet-101`](https://huggingface.co/facebook/detr-resnet-101). However you can use other compatabale models. Simply pass the new `MODEL_NAME` and `MODEL_PATH` to the make command. Make sure the model is downloaded and exists in the [models directory](../../../models/):
+As stated above, by default the model service will use [`facebook/detr-resnet-101`](https://huggingface.co/facebook/detr-resnet-101). However you can use other compatible models. Simply pass the new `MODEL_NAME` and `MODEL_PATH` to the make command. Make sure the model is downloaded and exists in the [models directory](../../../models/):
 
 ```bash
 # from path model_servers/object_detection_python from repo containers/ai-lab-recipes

diff --git a/training/amd-bootc/Containerfile b/training/amd-bootc/Containerfile
@@ -29,10 +29,11 @@ RUN grep -q /usr/lib/containers/storage /etc/containers/storage.conf || \
     sed -i -e '/additionalimage.*/a "/usr/lib/containers/storage",' \
         /etc/containers/storage.conf && \
     if [ -f "/run/.input/ilab" ]; then \
-          cp /run/.input/ilab /usr/local/bin/ilab; \
+          cp /run/.input/ilab /usr/bin/ilab; \
      else \
-          curl -o /usr/local/bin/ilab "https://raw.githubusercontent.com/containers/ai-lab-recipes/main/training/ilab-wrapper/ilab"; \
-    fi
+          curl -o /usr/bin/ilab "https://raw.githubusercontent.com/containers/ai-lab-recipes/main/training/ilab-wrapper/ilab"; \
+    fi \
+    && chmod +x /usr/bin/ilab
 
 ARG INSTRUCTLAB_IMAGE="quay.io/ai-lab/instructlab-amd:latest"
 
@@ -46,9 +47,9 @@ RUN if [ -n "${SSHPUBKEY}" ]; then \
 	    echo ${SSHPUBKEY} > /usr/ssh/root.keys && chmod 0600 /usr/ssh/root.keys; \
 fi
 
-RUN sed -i 's/__REPLACE_TRAIN_DEVICE__/cuda/' /usr/local/bin/ilab
-RUN sed -i 's/__REPLACE_CONTAINER_DEVICE__/nvidia.com\/gpu=all/' /usr/local/bin/ilab
-RUN sed -i "s%__REPLACE_CONTAINER_NAME__%${INSTRUCTLAB_IMAGE}%" /usr/local/bin/ilab
+RUN sed -i 's/__REPLACE_TRAIN_DEVICE__/cuda/' /usr/bin/ilab
+RUN sed -i 's/__REPLACE_CONTAINER_DEVICE__/nvidia.com\/gpu=all/' /usr/bin/ilab
+RUN sed -i "s%__REPLACE_CONTAINER_NAME__%${INSTRUCTLAB_IMAGE}%" /usr/bin/ilab
 
 # Added for running as an OCI Container to prevent Overlay on Overlay issues.
 VOLUME /var/lib/containers

diff --git a/training/nvidia-bootc/Containerfile b/training/nvidia-bootc/Containerfile
@@ -138,12 +138,18 @@ RUN mv /etc/selinux /etc/selinux.tmp \
         dnf module enable -y nvidia-driver:${DRIVER_BRANCH} && \
         dnf install -y nvidia-fabric-manager-${DRIVER_VERSION} libnvidia-nscq-${DRIVER_BRANCH}-${DRIVER_VERSION} ; \
     fi \
+    # Install rhc connect for insights telemetry gathering
+    && . /etc/os-release && if [ "${ID}" == "rhel" ]; then \
+        dnf install -y rhc rhc-worker-playbook; \
+        fi \
     && dnf clean all \
     && ln -s ../cloud-init.target /usr/lib/systemd/system/default.target.wants \
     && mv /etc/selinux.tmp /etc/selinux \
     && ln -s /usr/lib/systemd/system/nvidia-toolkit-firstboot.service /usr/lib/systemd/system/basic.target.wants/nvidia-toolkit-firstboot.service \
-    && echo "blacklist nouveau" > /etc/modprobe.d/blacklist_nouveau.conf
-
+    && echo "blacklist nouveau" > /etc/modprobe.d/blacklist_nouveau.conf \
+    && sed '/\[Unit\]/a ConditionPathExists = /dev/nvidia-nvswitchctl' /usr/lib/systemd/system/nvidia-fabricmanager.service \
+    && ln -s /usr/lib/systemd/system/nvidia-fabricmanager.service /etc/systemd/system/multi-user.target.wants/nvidia-fabricmanager.service \
+    && ln -s /usr/lib/systemd/system/nvidia-persistenced.service /etc/systemd/system/multi-user.target.wants/nvidia-persistenced.service
 
 ARG SSHPUBKEY
 
@@ -162,15 +168,16 @@ RUN grep -q /usr/lib/containers/storage /etc/containers/storage.conf || \
     sed -i -e '/additionalimage.*/a "/usr/lib/containers/storage",' \
 	/etc/containers/storage.conf && \
     if [ -f "/run/.input/ilab" ]; then \
-	  cp /run/.input/ilab /usr/local/bin/ilab; \
+	  cp /run/.input/ilab /usr/bin/ilab; \
      else \
-	  curl -o /usr/local/bin/ilab "https://raw.githubusercontent.com/containers/ai-lab-recipes/main/training/ilab-wrapper/ilab"; \
-    fi
+	  curl -o /usr/bin/ilab "https://raw.githubusercontent.com/containers/ai-lab-recipes/main/training/ilab-wrapper/ilab"; \
+    fi \
+    && chmod +x /usr/bin/ilab
 
 ARG INSTRUCTLAB_IMAGE="quay.io/ai-lab/instructlab-nvidia:latest"
 ARG GPU_COUNT_COMMAND="nvidia-ctk --quiet cdi list | grep -P nvidia.com/gpu='\\\\d+' | wc -l"
 
-RUN for i in /usr/local/bin/ilab*; do \
+RUN for i in /usr/bin/ilab*; do \
 	sed -i 's/__REPLACE_TRAIN_DEVICE__/cuda/' $i;  \
 	sed -i 's/__REPLACE_CONTAINER_DEVICE__/nvidia.com\/gpu=all/' $i; \
 	sed -i "s%__REPLACE_IMAGE_NAME__%${INSTRUCTLAB_IMAGE}%" $i; \