TECH·May 30, 2026Show HN: Tiny-vLLM – high performance LLM inference engine in C++ and CUDA | Hacker NewsHacker News
TECH·May 8, 2026LightSeek Foundation Releases TokenSpeed, an Open-Source LLM Inference Engine Targeting TensorRT-LLM-Level Performance for Agentic WorkloadsMarkTechPost
TECH·April 28, 2026Open source Xiaomi MiMo-V2.5 and V2.5-Pro are among the most efficient (and affordable) at agentic 'claw' tasksVentureBeat
TECH·April 21, 2026Moonshot AI launches open-source LLM Kimi-K2.6, claiming it outperforms GPT-5.4 and Claude Opus 4.6디지털투데이
