Geo News
Community curated by people like you
LatestAICryptoHealthWorld AffairsUS Politics

DeepSeek-V4-Flash stories

Oct 20, 2026

DeepSeek open-sources DeepInfer inference framework

DeepSeek has open-sourced DeepInfer, the inference framework that runs its production services and powers DeepSeek-V4.1-Flash. The release provides the engine behind one of the company's flagship models.

Oct 20, 2026·2 sources
00

Top claims

  • ▪DeepSeek reports overall revenue of US$38 per GPU-hour at valley pricing for DeepInfer
  • ▪DeepInfer builds require Linux, GCC 13 or later, Python 3.12, and CUDA 13 or CANN 9.2
  • ▪DeepInfer's DSpark feature uses a draft model that proposes 5 tokens per step with a Confidence Head predicting each draft token's acceptance rate

Topics

Chinese AI modelsDeepSeek-V4.1-FlashInferenceDeepSeekOpen-source AIEfficient inference