Deepseek Open‑Sources DeepInfer, an Optimized Inference Engine for Its V4.1‑Flash Model
Deepseek has released DeepInfer, an open‑source inference framework under the Apache License 2.0, designed to run its V4.1‑Flash model quickly and cheaply at scale. Built on vLLM with custom compute kernels and distributed processing across multiple chips, DeepInfer also includes a recipe that mimics the official Deepseek API token processing for self‑hosted deployments. The company says the move will lower compute costs, reduce energy use, and make AI more affordable, while also adding pricing pressure on Western providers such as OpenAI and Anthropic.
The open‑source engine enables cheaper, high‑performance inference for Deepseek’s models and could shift competitive dynamics in the AI market, especially for users and companies looking to self‑host or reduce reliance on Western cloud services.
Source: The Decoder · the-decoder.com