読書リサーチレーダー投資フレームワーク
ログイン / 新規登録
← 読解に戻る
ニューストピック · DeepSeek推理框架重大1 分で読めるDisconfirmAI 編集部

DeepSeek Open-Sources Internal Inference Framework DeepInfer for High-Throughput Deployment

DeepSeek has fully open-sourced its internal inference framework DeepInfer and the accompanying tokenization component deepseek-recipe, supporting both NVIDIA and Huawei Ascend platforms to help developers reduce compute costs for large-scale model deployment.

2026-10-20 17:05 GMT+8

Chinese AI company DeepSeek announced on October 20 that it is fully open-sourcing its internal inference framework, DeepInfer, along with its companion token encoding/decoding component, deepseek-recipe. This follows previous releases of model weights, the TileLang compiler tool, and inference operator libraries, marking a further opening of infrastructure-level assets.

The inference framework serves as a critical middle layer connecting model capabilities to actual services, responsible for orchestrating massive compute clusters. Its efficiency directly determines the compute cost and power consumption of AI services. DeepSeek stated that by sharing internal deployment experience, they aim to help developers and enterprises optimize throughput and latency for large-scale inference, thereby efficiently building private and public cloud deployments, reducing compute costs, and making intelligence accessible at lower prices to a broader audience.

According to the announcement, DeepInfer integrates high-performance operators with a deeply optimized inference engine, supporting distributed inference, speculative decoding, SWA Bounded Replay (Sliding Window Attention Bounded Replay), and structured output. It explicitly supports both NVIDIA and Huawei Ascend hardware platforms. DeepSeek has already implemented high-throughput, low-latency large-scale inference services for DeepSeek V4.1 Flash based on this framework. The simultaneously open-sourced deepseek-recipe is a production-grade token encoding/decoding component fully aligned with official API processing logic, ensuring the community receives a consistent API experience.

ログイン / 新規登録
読書リサーチレーダー投資フレームワーク

The open-source code repositories are available at: https://github.com/deepseek-ai/DeepInfer ↗ and https://github.com/deepseek-ai/deepseek-recipe ↗.

ソース

  • ithome.com↗
トピック

DeepSeek推理框架

中国AI公司DeepSeek于2026年10月20日正式开源其内部生产级推理框架DeepInfer及配套组件deepseek-recipe,旨在降低大规模模型部署的算力与能源成本。该框架支持英伟达Blackwell(SM100)和华为昇腾9…

4 ステップ5 件更新日 2026-11-07 19:16

経緯

  1. 2026-10-20DeepSeek宣布开源内部推理框架DeepInfer及编解码组件deepseek-recipe,支持英伟达与华为平台。ithome.com ↗
  2. 2026-10-20SiliconANGLE报道DeepSeek开源DeepInfer,指出部分核心调度代码暂未公开,并提及美国国土安全部此前要求联邦机构移除DeepSeek产品。siliconangle.com ↗
  3. 2026-10-21Latent Space发布AINews深度解析,披露DeepSeek声称的单集群日吞吐155万亿Token及每GPU小时38美元营收数据,引发关于利润率与回本周期的争议。latent.space ↗

未解決の問題

  • DeepInfer未公开的KV缓存管理和负载均衡代码何时能完全解耦并开源?
  • vLLM等现有开源引擎能否通过配置优化达到DeepInfer宣称的效率水平?
  • DeepSeek披露的经济数据(如38美元/GPU小时营收)在不同工作负载和硬件成本下的实际利润率是多少?

このスレッド内の他の記事

  • Latent Space AINews Analyzes DeepSeek's Open-Sourced Inference Engine DeepInfer: Details on 155T Daily Tokens and $38/GPU-Hour Revenue2026-10-23
  • DeepSeek releases open-source inference framework Deepinfer to cut self-hosting costs2026-10-22
トピック全文を読む →
リサーチを続ける →