z-AI
glm-5.3-flash
Container
z-AI
glm-5.3-flash

The GLM-5.3-Flash NIM container provides OpenAI-compatible inference APIs for deploying GLM-5.3-Flash on NVIDIA GPU-accelerated systems. It uses vLLM and includes NVIDIA Dynamo 1.4.1 in the same container.

LayerLabelCreated
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENTRYPOINT
/opt/nim/ffmpeg_entrypoint.sh
09/01/2026 10:03 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
nvs:1000
09/01/2026 10:03 AM UTC
sha256:62cc81fcb0378126cb0ddce96c300537e86fd662b8f0bc9eb683affeb3804e68RUN
TARGETARCH=amd64 NIM_NAME=zai-org/GLM-5.3-Flash NIM_MODEL_NAME=zai-org/GLM-5.3-Flash NIM_SERVED_MODEL_NAME=zai-org/GLM-5.3-Flash MANIFEST_FILE=model_manifest_prod.yaml set -eu; cache_root="/tmp/precompiled_cache/${TARGETARCH}"; mkdir -p /home/nvs/.cache /opt/nim/.cache; if [ -d "${cache_root}" ]; then for bundle in "${cache_root}"/*; do [ -d "${bundle}" ] ||
  continue; if [ -d "${bundle}/home/nvs/.cache" ]; then cp -a "${bundle}/home/nvs/.cache/." /home/nvs/.cache/; fi; if [ -d "${bundle}/opt/nim/.cache" ]; then cp -a "${bundle}/opt/nim/.cache/." /opt/nim/.cache/; fi; done; fi; chown -R 1000:1000 /home/nvs/.cache /opt/nim/.cache
09/01/2026 10:03 AM UTC
sha256:82412ebc04f89fbfe89fd80681f8bca7b6adf7ebd45388370e24c6c93cf16ceeRUN
TARGETARCH=amd64 NIM_NAME=zai-org/GLM-5.3-Flash NIM_MODEL_NAME=zai-org/GLM-5.3-Flash NIM_SERVED_MODEL_NAME=zai-org/GLM-5.3-Flash MANIFEST_FILE=model_manifest_prod.yaml set -eu; if [ "${TARGETARCH}" = "amd64" ]; then python3 -m pip install --break-system-packages --no-deps --force-reinstall /tmp/wheels/mooncake_transfer_engine_cuda13-0.3.13-cp312-cp312-manylinux_2_39_x86_64.whl; else echo "Skipping the x86_64 Mooncake wheel for ${TARGETARCH}."; fi
09/01/2026 10:03 AM UTC
sha256:1f85c10874b9a348868f3207acf22a3e429bec15581d7ec7ef68ec4a3f55cc72RUN
TARGETARCH=amd64 NIM_NAME=zai-org/GLM-5.3-Flash NIM_MODEL_NAME=zai-org/GLM-5.3-Flash NIM_SERVED_MODEL_NAME=zai-org/GLM-5.3-Flash MANIFEST_FILE=model_manifest_prod.yaml python3 -m pip install --break-system-packages --no-cache-dir --no-deps pillow==12.3.0 diffusers==0.38.0
09/01/2026 10:03 AM UTC
sha256:3db1cd2459f19473c85442ac010989f6803194ba3fdb2a11fdb43e3a85141826RUN
TARGETARCH=amd64 NIM_NAME=zai-org/GLM-5.3-Flash NIM_MODEL_NAME=zai-org/GLM-5.3-Flash NIM_SERVED_MODEL_NAME=zai-org/GLM-5.3-Flash MANIFEST_FILE=model_manifest_prod.yaml set -eu; for patch_file in /tmp/nim-patches/*.patch; do case "$(basename "${patch_file}")" in sglang_*) patch_root=/sgl-workspace/sglang ;; nim_stack_*) patch_root=/usr/local/lib/python3.12/dist-packages ;; *) echo "Unsupported patch target: ${patch_file}" >&2; exit 1 ;; esac; patch --directory="${patch_root}" --strip=1 --fuzz=0 < "${patch_file}"; done; rm -r /tmp/nim-patches
09/01/2026 10:02 AM UTC
sha256:41747abbbb92dbd040434df3bf97e53a7fdbf163c497ebe23793d6e3491eeb3eCOPY
patch/ /tmp/nim-patches/
09/01/2026 10:02 AM UTC
sha256:a9052d7ae5afc1f8f0856f4a9d157462ad34c4dd552e74b068c4a953651bb428COPY
heuristic_plugins/ /opt/nim/heuristic_plugin/
09/01/2026 10:02 AM UTC
sha256:91c79e4693166824ca2df9f505841fda7e37ff3a016f84fda8ddaaaccdae2f8dCOPY
banner.txt /opt/nim/banner.txt
09/01/2026 10:02 AM UTC
sha256:e090603bfc6e836a03f8e8b3b357cdaa66d66c13284c8a0fa8a49e356c8cede4COPY
tuning_configs/ /opt/nim/tuning_configs/
09/01/2026 10:02 AM 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.