error: creating server: Internal - s3:// file-system not supported. To enable, build with -DTRITON_ENABLE_S3=ON.

[shahizat]

Hello,

When I pass S3 path, I receive the following error: error: creating server: Internal - s3:// file-system not supported. To enable, build with -DTRITON_ENABLE_S3=ON

The pod is based on the nvcr.io/nvidia/tritonserver:24.07-py3-igpu image and is running on the NVIDIA Jetson AGX Orin development kit. If possible, please provide another image.

Thank you in advance for your help.

[shahizat]

Hello Nvidia team, If possible, could you please suggest the correct build command for setting up S3 support? I also noticed that the NCCL package is not included as well. To install it, I must use the command "sudo apt install libnccl2 libnccl-dev".

I was using the following command:

sudo python3 build.py \
    --build-parallel 10 \
    --no-force-clone \
    --target-platform igpu \
    --target-machine aarch64 \
    --filesystem s3 \
    --enable-gpu \
    --enable-mali-gpu \
    --enable-metrics \
    --enable-logging \
    --enable-stats \
    --enable-cpu-metrics \
    --enable-nvtx \
    --backend onnxruntime \
    --backend pytorch \
    --backend tensorflow \
    --backend python \
    --backend tensorrt \
    --endpoint http \
    --endpoint grpc \
    --min-compute-capability "5.3" \
    --image "base,nvcr.io/nvidia/${IMAGE_NAME}:${OFFICIAL_MIN_IMAGE_TAG}" \
    --image "gpu-base,nvcr.io/nvidia/${IMAGE_NAME}:${OFFICIAL_MIN_IMAGE_TAG}

[oandreeva-nv]

Hi @shahizat , intersting, --filesystem s3 should ideally take care of S3. Is it possible to share a build log?

As for dependencies, to determine what dependencies are required by the build, run build.py with the --dryrun flag, and then looking in the build subdirectory at Dockerfile.buildbase [reference]

[shahizat]

Hi @oandreeva-nv, thanks for your reply. I've finally been able to build it, Here is a link to my blog post: https://www.hackster.io/shahizat/triton-inference-server-on-nvidia-jetson-using-k3s-and-minio-cbcfe3