# DeepSeek releases DeepInfer inference framework as open source

> DeepSeek has made its DeepInfer framework, used for the DeepSeek‑V4.1‑Flash model, available under an Apache 2.0 license.

Oossa · 2026-10-20 · https://oossa.com/en/deepseek-releases-deepinfer-inference-framework-as-open-source

DeepSeek announced that it is open‑sourcing DeepInfer, the inference engine that runs its DeepSeek‑V4.1‑Flash model in production. The framework is released under the Apache 2.0 license. It is built for NVIDIA SM100 GPUs and Huawei Ascend 950 NPUs and supports only offline inference.

## The facts

- DeepInfer is released under the Apache 2.0 license.
- It targets NVIDIA SM100 GPUs and Huawei Ascend 950 NPUs.

## Why it matters

Developers can now use DeepSeek’s production‑grade inference code on supported hardware without building their own stack.

## Sources & references

1. [DeepSeek Open-Sources DeepInfer, the Inference Framework Behind DeepSeek-V4.1-Flash](https://www.marktechpost.com/2026/10/20/deepseek-deepinfer-open-source-inference-framework/) – MarkTechPost, 2026-10-20
2. [DeepSeek open-sources DeepInfer, the inference framework behind its production services](https://siliconangle.com/2026/10/20/deepseek-open-sources-deepinfer-the-inference-framework-behind-its-production-services/) – SiliconANGLE, 2026-10-20
3. [Deepseek open-sources the inference engine that powers its fastest and cheapest AI model](https://the-decoder.com/deepseek-open-sources-the-inference-engine-that-powers-its-fastest-and-cheapest-ai-model/) – The Decoder, 2026-10-20
4. [[AINews] DeepSeek DeepInfer: Open Source SOTA Inference running 155T toks/day/cluster making $22m/day at ~80% margin for a 81 day payback](https://www.latent.space/p/ainews-deepseek-deepinfer-open-source) – Latent Space, 2026-10-21

Last updated: 2026-10-21