lightweight system-level observability for AI Agents
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
Next-gen AI+IoT framework for T2/T3/T5AI/ESP32/and more – Fast IoT and AI Agent hardware integration
React Native binding of llama.cpp
Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4