Skip to main content
DeepSeek AI
DeepSeek-V4-Pro-0813
Container
DeepSeek AI
DeepSeek-V4-Pro-0813

DeepSeek-V4-Pro-0813 is DeepSeek-AI’s official release, delivered as an NVIDIA NIM container for OpenAI-compatible text generation, reasoning, coding, and agentic tool-use workflows.

LayerLabelCreated
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
nvs:1000
09/03/2026 6:12 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NIM_TRUST_CUSTOM_CODE=true
09/03/2026 6:12 AM UTC
sha256:0652404effd97fe83f10f042b73ab44022199e06471565ea4c935be9214d9045RUN
MODEL_NAME=deepseek-ai/DeepSeek-V4-Pro-0813 /bin/bash -lc set -e &&
  mkdir -p /opt/nim/etc/default /opt/nim/tuning_configs &&
  mv /tmp/nim-build/model_manifest_dsv4_with_checksum.yaml /opt/nim/etc/default/model_manifest.yaml &&
  cp -a /tmp/nim-build/tuning_configs/. /opt/nim/tuning_configs/ &&
  mv /tmp/nim-build/LICENSE /opt/nim/LICENSE &&
  mv /tmp/nim-build/MODEL_LICENSE /opt/nim/MODEL_LICENSE &&
  mv /tmp/nim-build/VERSION /opt/nim/VERSION &&
  mv /tmp/nim-build/notice_file.txt /opt/nim/notice_file.txt &&
  cd /sgl-workspace/sglang &&
  chmod u+w python/sglang/srt/speculative/dflash_utils.py python/sglang/srt/speculative/dspark_components/dspark_verify.py python/sglang/srt/entrypoints/openai/serving_chat.py &&
  patch -p1 --forward --backup < /tmp/nim-build/fix-min-tokens-dspark-verify.patch &&
  patch -p1 --forward --backup < /tmp/nim-build/fix-tool-choice-none-dsv.patch &&
  rm -rf /tmp/nim-build
09/03/2026 6:12 AM UTC
sha256:a09e34040b5f2ceb5afe2a128b45e8abf599c94714f06862dffcc7200baad57dCOPY
./model_manifest_dsv4_with_checksum.yaml ./LICENSE ./MODEL_LICENSE ./VERSION ./notice_file.txt ./patches/fix-min-tokens-dspark-verify.patch ./patches/fix-tool-choice-none-dsv.patch /tmp/nim-build/
09/03/2026 6:12 AM UTC
sha256:deae5d9cc5d021dfffc887bc7e06e917efb90cc45351e8c780024b2230b3c130COPY
./tuning_configs /tmp/nim-build/tuning_configs/
08/24/2026 8:15 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
PRODUCT_NAME=NVIDIA Inference Microservice LLM / VLM NIM
08/24/2026 8:15 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NIM_MODEL_NAME=deepseek-ai/DeepSeek-V4-Pro-0813
08/24/2026 8:15 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ENV
NIM_SERVED_MODEL_NAME=deepseek-ai/DeepSeek-V4-Pro-0813
08/24/2026 8:15 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4ARG
MODEL_NAME=deepseek-ai/DeepSeek-V4-Pro-0813
08/24/2026 8:15 AM UTC
sha256:a3ed95caeb02ffe68cdd9fd84406680ae93d633cb16422d00e8a7c22955b46d4USER
root
08/24/2026 8:15 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.