DeepSeek open-sourced DeepInfer, its inference framework, on October 20, 2026. Released under the Apache 2.0 license, this tool enables businesses to deploy the company’s AI models at lower compute and energy costs. DeepInfer supports Nvidia SM100 GPUs as well as Huawei Ascend 950 chips, and includes features like speculative decoding and distributed inference. This release follows the launch of the V4.1-Flash-1017 model, whose DeepSWE score rose from 74.2 to 77.0. This initiative aligns with DeepSeek’s strategy of democratizing access to artificial intelligence by sharing both models and infrastructure.
Source: Read the original article
Disclaimer: this content is for information purposes only and is not financial advice. Cryptocurrencies are highly volatile: you may lose all of your capital. Always do your own research. Legal notice
