Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported
Python
README/pyproject: drop Apple-Silicon-only framing; backend-isolated, multi-platform roadmap
linyubupa4d78aeb5bffb
diff --git a/README.md b/README.mdindex c74f2e9..3778a0d 100644--- a/README.md+++ b/README.md@@ -1,7 +1,8 @@# edge0-**edge0** 是一个面向 Apple Silicon 的开源流式 MoE 推理框架:把「SSD 专家 offload +-并行 LoRA + prerouter 路由预判」方案抽象成可扩展的通用框架,开箱支持两个模型:+**edge0** 是一个开源的流式 MoE 推理框架:把「SSD 专家 offload ++并行 LoRA + prerouter 路由预判」方案抽象成可扩展的通用框架,后端隔离设计+(当前 MLX / Apple Silicon,后续将适配其它平台),开箱支持两个模型:| 模型 | 说明 | 推理档 ||---|---|---|diff --git a/pyproject.toml b/pyproject.tomlindex 3fe8d0b..14b90f7 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"[project]name = "edge0"version = "0.1.0"-description = "edge0: streaming MoE inference for Apple Silicon — SSD expert offload, parallel LoRA, prerouter routing prediction. Backend-isolated (MLX now, CUDA-ready)."+description = "edge0: streaming MoE inference framework — SSD expert offload, parallel LoRA, prerouter routing prediction. Backend-isolated (MLX now, more platforms coming)."readme = "README.md"requires-python = ">=3.10"license = { text = "Apache-2.0" }