Upstar existe aussi en français.

Voir cette page en français

Upstar ranks the fastest-rising GitHub projects every hour, across 69 topics. Browse topics

musicurgy /

delta-inference-engine

Delta Inference Engine: DeepSeek-V4.1-Flash on one NVIDIA GPU, natively on Windows (OpenAI-compatible server)

#30 in LLM serving C++ 53 stars New

Updated 20 min ago

Why now

Version 0.92 came out on October 27.

+53 stars gained this week

Stars gained each day, last 30 days

Oct 4Oct 19Today
This week Before

In short

It needs an NVIDIA RTX GPU with at least 12 GB, 128 GB of RAM and about 385 GB of fast NVMe storage, and is started by double-clicking a launcher that sets up the rest.

Summary written by AI from the repository’s description and README.

musicurgy / delta-inference-engine
View on GitHub(opens in new tab)