DeepSeek releases DeepInfer for running its AI models at scale

The framework supports DeepSeek-V4.1-Flash but leaves out components developers need to build a complete inference service. Quartz reports support for both Nvidia and Huawei chips, while Bloomberg says the release could make DeepSeek's technology cheaper and easier for businesses to run by opening up its large-scale serving software.

• According to The Next Web, the code is available on GitHub under the Apache 2.0 license.

Covered by 8 publishers within 9 hours of the first report.

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

Reporting8

RTW RuntimeWire DeepSeek opens its inference engine, leaving service plumbing to developers · RuntimeWire Staff 5:52 AM

BL Bloomberg DeepSeek Unveils Open-Source Tool to Help Cut AI Operating Costs · Saritha Rai 8:45 AM

QZ Quartz DeepSeek is open-sourcing the software it uses to run its AI models at scale · Cris Tolomia 9:40 AM

TNW The Next Web DeepSeek open-sources DeepInfer, the engine that runs its AI models · Ana Maria Constantin 10:08 AM

MT MarkTechPost DeepSeek Open-Sources DeepInfer, the Inference Framework Behind DeepSeek-V4.1-Flash · Asif Razzaq 10:31 AM

TNS The New Stack DeepSeek open-sources the inference engine behind its API. And Huawei gets equal billing with Nvidia. · Paul Sawers 10:58 AM

GZ Gizmodo DeepSeek Dials Up the Pressure on OpenAI and Anthropic With Open-Source Inference Tool · Webb Wright 12:45 PM

PY PYMNTS DeepSeek Open Sources Inference Tech to Lower AI Costs · PYMNTS 2:52 PM

Related

DT DeepSeek works with Huawei on designs for future AI chips October 19

DT DeepSeek releases V4.1-Flash update targeting more efficient AI agents October 18

DT DeepSeek reportedly agrees to lead funding for robotics startup Winverse AI October 12

TRP Nvidia Launches Three Nemotron AI Models, Including Two for Local AI Agents October 15

Topics DeepSeekHuaweiNvidia