jundot / omlx
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
活跃维护 Apache 2.0 Python Tracked
23.1k 2.1k 8 小时前
CIPyPI
apple-silicon inference-server llm macos mlx openai-api
星标趋势
数据积累中，暂无足够数据生成趋势图
AI 分析
项目摘要
jundot/omlx: LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
为什么值得关注
High popularity with 21,853 stars, active contributor community (222 contributors), frequent releases.
优势
- Large and active community
- Continuous integration configured
- Test suite present
局限性
- Limited documentation
分析模型：fallback | 分析时间：1 个月前