NVIDIA
DeepSeek-V4-Flash-0731 NIM
Container
NVIDIA
DeepSeek-V4-Flash-0731 NIM

DeepSeek-V4-Flash-0731 NIM inference container for OpenAI-compatible text generation, coding, reasoning, long-context, and agentic workflows.

LayerLabelCreated
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
nvs:1000
08/13/2026 5:21 AM UTC
sha256:5487081198be8c18cbb3460998da3b7360c0ad6d5c7867178b440226a1458becCOPY
banner.txt /opt/nim/banner.txt
08/13/2026 5:21 AM UTC
sha256:4d553abf20edfcc4e74d281f5d99445403aebeab65ac2115f19b483f490eb685COPY
heuristic_plugins/ /opt/nim/heuristic_plugin/
08/13/2026 5:21 AM UTC
sha256:a79ee821219e79269463c89232f4f929f6ffdbe10fc7c31123f24056925892d7COPY
hw_helper.py /opt/nim/hw_helper.py
08/13/2026 5:21 AM UTC
sha256:88b7fd2197350dfdb190de9429ee8aaf05f62f9777e33d9d5e00c5ae0ddea5beCOPY
tuning_configs/* /opt/nim/
08/13/2026 5:21 AM UTC
sha256:f34a174c679ca74096868271fe839c522763d95c75e60fdca111aa92a3c36057RUN
TARGETARCH=amd64 NIM_NAME=deepseek-ai/DeepSeek-V4-Flash-0731 NIM_MODEL_NAME=deepseek-ai/DeepSeek-V4-Flash-0731 MANIFEST_FILE=model_manifest_prod.yaml python -m pip uninstall -y mooncake-transfer-engine-cuda13 &&
  ! python -c "import mooncake" 2>/dev/null &&
  python -c "import sglang.srt.managers.scheduler, nimlib.llm.profile_selection"
08/13/2026 5:21 AM UTC
sha256:09bfa6564c745e60fd5e6d0f18ce21b86ef8be10b062b9e148fe0b987db59033RUN
TARGETARCH=amd64 NIM_NAME=deepseek-ai/DeepSeek-V4-Flash-0731 NIM_MODEL_NAME=deepseek-ai/DeepSeek-V4-Flash-0731 MANIFEST_FILE=model_manifest_prod.yaml python -m pip install --no-cache-dir --upgrade "pillow==12.3.0" &&
  python -c "import PIL; assert PIL.__version__ == '12.3.0', PIL.__version__"
08/13/2026 5:21 AM UTC
sha256:8faf18aba913c4e298c849c617cbdfe54341af53b34ee31091171326247db05aRUN
TARGETARCH=amd64 NIM_NAME=deepseek-ai/DeepSeek-V4-Flash-0731 NIM_MODEL_NAME=deepseek-ai/DeepSeek-V4-Flash-0731 MANIFEST_FILE=model_manifest_prod.yaml if [ -d /usr/local/lib/python3.12/dist-packages/flashinfer_cubin ]; then mkdir -p /usr/local/lib/python3.12/dist-packages/flashinfer_cubin/cubins &&
  chown -R nvs:1000 /usr/local/lib/python3.12/dist-packages/flashinfer_cubin/cubins; fi
08/13/2026 5:21 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NIM_CONFIG_FILE=
08/13/2026 5:21 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NIM_HEURISTIC_PLUGIN_DIR=/opt/nim/heuristic_plugin/
08/13/2026 5:21 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.