DeepSeek Open-Sources DeepInfer Inference Engine
DeepSeek open-sourced the DeepInfer project on GitHub, an inference engine powering the DeepSeek-V4.1-Flash model. The system features technologies like MoE expert parallelism and custom Kernels, reportedly processing about 155 quadrillion tokens per day on a single cluster to optimize large-scale inference efficiency.
Summarized by AI from one outlet
Source
Latest
- Open source
Microsoft releases TokenEconomizer plugin to cut costs
Microsoft Research and UC Berkeley released TokenEconomizer, an open-source plugin that reduces coding agent costs by 18.4% to 30.9% on SWE-Bench. It achieves this by learning from past sessions without modifying the agent architecture.
- Open source
Xiaomi open-sources 0.8B OCR model
Xiaomi open-sourced Xiaomi-OCR-0, a lightweight document understanding model with 0.8B parameters. Based on the Qwen3.5 foundation, it covers document parsing, key information extraction, and OCR visual question answering, with weights and code available on Hugging Face.
All news → · All rights belong to the original creators