[GH-ISSUE #26] Request for Dockerfile or Prebuilt Docker Container #20

New issue

Closed

opened 2026-10-26 21:11:06 +00:00 by bsakaguchi · 3 comments

bsakaguchi commented

2026-10-26 21:11:06 +00:00

Owner

Originally created by @Emilio942 on GitHub (Dec 29, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-V3/issues/26

Hi,

I’m using the DeepSeek-V3-Base model and have set up everything manually so far. However, it would be much more convenient if there were an official Dockerfile or prebuilt Docker container available for easier integration.

Does an official Docker setup for this model exist? If not, would it be possible to provide one?
A prebuilt container bundling the model and its dependencies would greatly simplify the deployment process for users.

Thank you in advance for your help!
Looking forward to your response.

Best regards,
Emilio Frittrang

Are there any specific optimizations or configurations required to efficiently run the DeepSeek-V3-Base model in a Docker environment?

Base image

FROM python:3.10-slim

Install git and clean up temporary files

RUN apt-get update && apt-get install -y git && apt-get clean && rm -rf /var/lib/apt/lists/*

Set working directory

WORKDIR /app

Clone the repository and install dependencies

RUN git clone https://github.com/deepseek-ai/DeepSeek-V3.git . &&
pip install --no-cache-dir -r inference/requirements.txt

Default command to run the model

CMD ["python", "inference/generate.py"]

Originally created by @Emilio942 on GitHub (Dec 29, 2024). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-V3/issues/26 Hi, I’m using the `DeepSeek-V3-Base` model and have set up everything manually so far. However, it would be much more convenient if there were an official Dockerfile or prebuilt Docker container available for easier integration. Does an official Docker setup for this model exist? If not, would it be possible to provide one? A prebuilt container bundling the model and its dependencies would greatly simplify the deployment process for users. Thank you in advance for your help! Looking forward to your response. Best regards, Emilio Frittrang Are there any specific optimizations or configurations required to efficiently run the DeepSeek-V3-Base model in a Docker environment? # Base image FROM python:3.10-slim # Install git and clean up temporary files RUN apt-get update && apt-get install -y git && apt-get clean && rm -rf /var/lib/apt/lists/* # Set working directory WORKDIR /app # Clone the repository and install dependencies RUN git clone https://github.com/deepseek-ai/DeepSeek-V3.git . && \ pip install --no-cache-dir -r inference/requirements.txt # Default command to run the model CMD ["python", "inference/generate.py"]

bsakaguchi closed this issue

2026-10-26 21:11:06 +00:00

bsakaguchi commented

2026-10-26 21:11:08 +00:00

Author

Owner

@GeeeekExplorer commented on GitHub (Dec 31, 2024):

Actually the infer demo is slow but the compatibility is good because we built the demo entirely using pytorch and triton code. No special configuration is required.

@GeeeekExplorer commented on GitHub (Dec 31, 2024): Actually the infer demo is slow but the compatibility is good because we built the demo entirely using pytorch and triton code. No special configuration is required.

bsakaguchi commented

2026-10-26 21:11:08 +00:00

Author

Owner

@mowentian commented on GitHub (Dec 31, 2024):

For actual deployment, you can use the Docker files provided by sglang, lmdeploy, or vllm, among others. The community support for us is also quite robust.

@mowentian commented on GitHub (Dec 31, 2024): For actual deployment, you can use the Docker files provided by sglang, lmdeploy, or vllm, among others. The community support for us is also quite robust.

bsakaguchi commented

2026-10-26 21:11:09 +00:00

Author

Owner

@Emilio942 commented on GitHub (Jan 5, 2025):

thank you.

@Emilio942 commented on GitHub (Jan 5, 2025): thank you.

bsakaguchi referenced this issue

2026-10-26 21:15:47 +00:00

[GH-ISSUE #348] [BUG]调用 DeepSeek API 时返回与 OpenAI 相关的内容 #160

bsakaguchi referenced this issue

2026-10-26 21:29:01 +00:00