cactus-compute /engine面向手机、可穿戴设备、智能家居和机器人的量化、内核、运行时和推理引擎。 C++6188#ai#android#arm#edge#edge-ai#framework原文站内解读 →
georgebon5 /minillm-cppFrom-scratch C++ LLM inference engine — runs SmolLM2 (135M–1.7B) on CPU with hand-written NEON SIMD, INT8 quantization, and a live web UI. C++0