# The New Stack — DeepSeek open-sources the inference engine behind its API. And Huawei gets equal billing with Nvidia.

- Company: The New Stack (thenewstack.io)
- Announced: 2026-10-20T14:58:36+00:00
- Category: developer-tool-release
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://thenewstack.io/deepseek-deepinfer-huawei-nvidia/
- Record: https://forck.live/items/25263-deepseek-open-sources-the-inference-engine-behind-its-api-and-huawei-gets
- Subject: Reporting
- Models affected: DeepSeek-V4.1-Flash, DeepSeek-V4.1-Flash-1017
- License: Apache 2.0

DeepSeek has open-sourced DeepInfer, the inference engine it uses to serve its models in production, a step it said last year was not yet practical. The framework lets developers run DeepSeek's V4.1 Flash model on their own infrastructure with many of the optimizations behind the company's API, and support for future DeepSeek models is planned. DeepSeek says it is sharing its production stack to help the community lower compute costs, reduce energy use and make AI more affordable. Released under the Apache 2.0 license, DeepInfer bundles optimized computing kernels and communication libraries, including the previously open-sourced FlashMLA, DeepGEMM and DeepEP, plus multi-chip distribution, speculative decoding, asynchronous scheduling and structured outputs. A companion library, deepseek-recipe, handles how API requests become model inputs and how outputs become responses, and is available for Rust and Python. The public software currently supports offline inference with the core features needed for serving at scale, but KV cache management, cross-machine stage separation and replica load balancing are still missing. Supported hardware is Nvidia's SM100 architecture, used in Blackwell data center GPUs, and Huawei's Ascend 950 NPU series, while older Nvidia architectures such as Hopper are absent.

## Evidence

Verbatim from https://thenewstack.io/deepseek-deepinfer-huawei-nvidia/:

> Released under the Apache 2.0 license, DeepInfer includes optimized computing kernels and communication libraries, including DeepSeek’s previously open-sourced FlashMLA, DeepGEMM, and DeepEP, alongside mechanisms for distributing inference across multiple chips.

---

Record: https://forck.live/items/25263-deepseek-open-sources-the-inference-engine-behind-its-api-and-huawei-gets
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md