Show HN: Shard – Distributed AI Inference Across Multiple Computers
Local LLM inference engine with pre-flight model fit checks, GGUF/PyTorch backends, OpenAI-compatible API, and LAN VRAM pooling (experimental P2P/WAN relay) - avelone123123/shard
Local LLM inference engine with pre-flight model fit checks, GGUF/PyTorch backends, OpenAI-compatible API, and LAN VRAM pooling (experimental P2P/WAN relay) - avelone123123/shard