| ARG RELEASE |
| ARG LAUNCHPAD_BUILD_ARCH |
| LABEL org.opencontainers.image.ref.name=ubuntu |
| LABEL org.opencontainers.image.version=24.04 |
| ADD file:6df775300d76441aa33f31b22c1afce8dfe35c8ffbc14ef27c27009235b12a95 in / |
| CMD ["/bin/bash"] |
| ENV NVARCH=x86_64 |
| ENV NVIDIA_REQUIRE_CUDA=cuda>=12.8 brand=unknown,driver>=470,driver<471 brand=grid,driver>=470,driver<471 brand=tesla,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=vapps,driver>=470,driver<471 brand=vpc,driver>=470,driver<471 brand=vcs,driver>=470,driver<471 brand=vws,driver>=470,driver<471 brand=cloudgaming,driver>=470,driver<471 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 |
| ENV NV_CUDA_CUDART_VERSION=12.8.90-1 |
| ARG TARGETARCH |
| LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com> |
| RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends gnupg2 curl ca-certificates && curl -fsSL https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH}/3bf863cc.pub | apt-key add - && echo "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH} /" > /etc/apt/sources.list.d/cuda.list && apt-get purge --autoremove -y curl && rm -rf /var/lib/apt/lists/* # buildkit |
| ENV CUDA_VERSION=12.8.1 |
| RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-12-8=${NV_CUDA_CUDART_VERSION} cuda-compat-12-8 && rm -rf /var/lib/apt/lists/* # buildkit |
| RUN |1 TARGETARCH=amd64 /bin/sh -c echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit |
| ENV PATH=/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin |
| ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64 |
| COPY NGC-DL-CONTAINER-LICENSE / # buildkit |
| ENV NVIDIA_VISIBLE_DEVICES=all |
| ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility |
| ENV NV_CUDA_LIB_VERSION=12.8.1-1 |
| ENV NV_NVTX_VERSION=12.8.90-1 |
| ENV NV_LIBNPP_VERSION=12.3.3.100-1 |
| ENV NV_LIBNPP_PACKAGE=libnpp-12-8=12.3.3.100-1 |
| ENV NV_LIBCUSPARSE_VERSION=12.5.8.93-1 |
| ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-8 |
| ENV NV_LIBCUBLAS_VERSION=12.8.4.1-1 |
| ENV NV_LIBCUBLAS_PACKAGE=libcublas-12-8=12.8.4.1-1 |
| ENV NV_LIBNCCL_PACKAGE_NAME=libnccl2 |
| ENV NV_LIBNCCL_PACKAGE_VERSION=2.25.1-1 |
| ENV NCCL_VERSION=2.25.1-1 |
| ENV NV_LIBNCCL_PACKAGE=libnccl2=2.25.1-1+cuda12.8 |
| ARG TARGETARCH |
| LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com> |
| RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-libraries-12-8=${NV_CUDA_LIB_VERSION} ${NV_LIBNPP_PACKAGE} cuda-nvtx-12-8=${NV_NVTX_VERSION} libcusparse-12-8=${NV_LIBCUSPARSE_VERSION} ${NV_LIBCUBLAS_PACKAGE} ${NV_LIBNCCL_PACKAGE} && rm -rf /var/lib/apt/lists/* # buildkit |
| RUN |1 TARGETARCH=amd64 /bin/sh -c apt-mark hold ${NV_LIBCUBLAS_PACKAGE_NAME} ${NV_LIBNCCL_PACKAGE_NAME} # buildkit |
| COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit |
| COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit |
| ENV NVIDIA_PRODUCT_NAME=CUDA |
| ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"] |
| ENV NV_CUDNN_VERSION=9.8.0.87-1 |
| ENV NV_CUDNN_PACKAGE_NAME=libcudnn9-cuda-12 |
| ENV NV_CUDNN_PACKAGE=libcudnn9-cuda-12=9.8.0.87-1 |
| ARG TARGETARCH |
| LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com> |
| LABEL com.nvidia.cudnn.version=9.8.0.87-1 |
| RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends ${NV_CUDNN_PACKAGE} && apt-mark hold ${NV_CUDNN_PACKAGE_NAME} && rm -rf /var/lib/apt/lists/* # buildkit |
| ARG VERSION=0.1.0 |
| ARG VCS_REF=unknown |
| ARG SOURCE_REPOSITORY=https://git.ramblingcoder.com/ramblingcoder/nemotron-streaming-asr-docker |
| ARG NEMO_SPEECH_VERSION=0.1.0 |
| ARG NEMO_SPEECH_REVISION=4f9676226f667d14608487df744f375db87127f8 |
| LABEL org.opencontainers.image.title=Nemotron Streaming ASR service org.opencontainers.image.description=OpenAI-compatible and realtime English Nemotron ASR CUDA service org.opencontainers.image.version=0.1.0 org.opencontainers.image.revision=cd0657da2d9bfedf25b947aa194102d97b7153a6 org.opencontainers.image.source=https://git.ramblingcoder.com/ramblingcoder/nemotron-streaming-asr-docker org.opencontainers.image.licenses=MIT AND Apache-2.0 io.ramblingcoder.nemotron-streaming-asr.upstream-version=0.1.0 io.ramblingcoder.nemotron-streaming-asr.upstream-revision=4f9676226f667d14608487df744f375db87127f8 |
| ADD https://github.com/NVIDIA/NeMo-Speech.cpp/releases/download/v0.1.0/nemo-speech-0.1.0-linux-x86_64-cuda.tar.gz /tmp/nemo-speech.tar.gz # buildkit |
| RUN |5 VERSION=0.1.0 VCS_REF=cd0657da2d9bfedf25b947aa194102d97b7153a6 SOURCE_REPOSITORY=https://git.ramblingcoder.com/ramblingcoder/nemotron-streaming-asr-docker NEMO_SPEECH_VERSION=0.1.0 NEMO_SPEECH_REVISION=4f9676226f667d14608487df744f375db87127f8 /bin/sh -c mkdir -p /opt/nemo-speech /usr/share/licenses/nemotron-streaming-asr && tar -xzf /tmp/nemo-speech.tar.gz --strip-components=1 -C /opt/nemo-speech && rm /tmp/nemo-speech.tar.gz && test -x /opt/nemo-speech/bin/nemo-speech && groupadd --system --gid 10001 asr && useradd --system --uid 10001 --gid 10001 --no-create-home --home-dir /tmp asr # buildkit |
| ADD https://raw.githubusercontent.com/NVIDIA/NeMo-Speech.cpp/4f9676226f667d14608487df744f375db87127f8/LICENSE /usr/share/licenses/nemotron-streaming-asr/NeMo-Speech.cpp-LICENSE # buildkit |
| COPY LICENSE NOTICE /usr/share/licenses/nemotron-streaming-asr/ # buildkit |
| RUN |5 VERSION=0.1.0 VCS_REF=cd0657da2d9bfedf25b947aa194102d97b7153a6 SOURCE_REPOSITORY=https://git.ramblingcoder.com/ramblingcoder/nemotron-streaming-asr-docker NEMO_SPEECH_VERSION=0.1.0 NEMO_SPEECH_REVISION=4f9676226f667d14608487df744f375db87127f8 /bin/sh -c chmod 0644 /usr/share/licenses/nemotron-streaming-asr/* # buildkit |
| ENV PATH=/opt/nemo-speech/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin LD_LIBRARY_PATH=/opt/nemo-speech/lib HOME=/tmp XDG_CACHE_HOME=/tmp/.cache CUDA_CACHE_PATH=/tmp/cuda-cache NVIDIA_VISIBLE_DEVICES=all NVIDIA_DRIVER_CAPABILITIES=compute,utility |
| USER 10001:10001 |
| EXPOSE map[8000/tcp:{}] |
| HEALTHCHECK &{["CMD-SHELL" "nemo-speech health --url http://127.0.0.1:8000/ready"] "30s" "3s" "2m0s" "0s" '\x03'} |
| ENTRYPOINT ["nemo-speech"] |
| CMD ["serve" "--host" "0.0.0.0" "--port" "8000" "--no-ui" "--threads" "2" "--max-upload-mb" "64" "--read-timeout" "120" "--write-timeout" "120" "--access-log" "--log-format" "json" "--asr.model.path" "/model/nemotron-speech-streaming-en-0.6b.q8_0.gguf" "--asr.backend.gpu" "0" "--asr.streaming.rnnt_right_context" "6" "--asr.batching.enabled=false" "--asr.endpointing.enable=true" "--asr.endpointing.stop_history_eou_ms" "800"] |
