Home / 𧱠AI Foundation Stack / ①Inference / Serving
brontoguana/krasis
Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
Commercial license
License unclearNOASSERTION
ζͺζ¨η€Ίζζ¬ β εη¨εεεΏ η’Ίθͺ(ι θ¨θ¦ηΊδΏηζζζ¬ε©)
Topics
cpu-inferencegguf-model-supportgpu-inferencehigh-performance-inferencehybrid-inferenceinference-engineinference-optimizationlarge-language-modelsllama-cpp-alternativellm-inferencemixture-of-expertstransformer
Ad