NVIDIA
NVIDIA MTBench
Container
NVIDIA
NVIDIA MTBench

NVIDIA NeMo Evaluator-compatible container with MTBench support. Based on FastChat available at: https://github.com/lm-sys/FastChat

  • LayerLabelCreated
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4LABEL
    org.opencontainers.image.licenses=3rd_party_licenses.txt
    08/04/2025 3:01 PM UTC
    sha256:f2da50c52dce1db06e060105e543cc03ebf27e877465aeff69ab546ccaf2f21aCOPY
    3rd_party_licenses.txt .
    08/04/2025 3:01 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
    THIRD_PARTY_LICENSES_FILE=3rd_party_licenses.txt
    08/04/2025 3:01 PM UTC
    sha256:bdc428cc7f01ba5310647873067190c84b237d9f3b2e350bd97a2a5549b915c3RUN
    pip uninstall -y nvidia-eval-commons-internal
    08/04/2025 3:01 PM UTC
    sha256:b62375b84aaa520641ddb77ce37b31848b59dd9f7959292632e7a14cb117ef05COPY
    tests/* /workspace/tests/
    08/04/2025 1:44 PM UTC
    sha256:9f25223ad83dd8b8f1a6adaa1b9d0cf0408a2660a2cf685ea23432969fd8d06cRUN
    CI_COMMIT_SHA=360de12fe9a031dd0475ee807b1f04531e9917cb EVAL_WHEEL_VERSION=25.07.1 PKG_URL=gitlab-master.nvidia.com/api/v4/projects/153108/packages/pypi/simple printf '#!/bin/bash\ncore-evals-mtbench "$@"' > /usr/bin/nv-eval &&
      chmod +x /usr/bin/nv-eval &&
      printf '#!/bin/bash\ncore-evals-mtbench "$@"' > /usr/bin/nv_eval &&
      chmod +x /usr/bin/nv_eval
    08/04/2025 1:44 PM UTC
    sha256:b114a51acaa56eec8e220e0f7bfeece5f3717a7702a252e35a2b447e88bd6493RUN
    CI_COMMIT_SHA=360de12fe9a031dd0475ee807b1f04531e9917cb EVAL_WHEEL_VERSION=25.07.1 PKG_URL=gitlab-master.nvidia.com/api/v4/projects/153108/packages/pypi/simple pip install nvidia_mtbench_evaluator==${EVAL_WHEEL_VERSION} --no-cache-dir --index-url https://gitlab-ci-token:$(cat /run/secrets/ci_job_token)@${PKG_URL}
    08/04/2025 1:44 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    OPENAI_SCOPE=azureopenai-readwrite
    08/04/2025 1:44 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    OPENAI_MODEL_VERSION=2024-06-01
    08/04/2025 1:44 PM UTC
    sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
    OPENAI_MODEL_URL=https://prod.api.nvidia.com/llm/v1/azure/
    08/04/2025 1:44 PM UTC

    NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.