From the creator of Redis; run LLM locally with ds4

一句话概要

Docs, benchmarks and setup notes for ds4, antirez’s C inference engine for DeepSeek V4/V4.1, Qwen3.8 Flash Next and GLM 5.x on Metal, CUDA and ROCm.

原文开头节选

DwarfStar 4 is a narrow C inference engine for high-memory Mac, CUDA and ROCm machines. It supports DeepSeek V4 and V4.1 Flash, GLM 5.x and Qwen3.8 Flash Next, with text and vision models, local APIs, a CLI and a native agent in one stack.

SUPPORTED: DEEPSEEK V4 / V4.1 + GLM 5.x + QWEN3.8 · MIT LICENSE · C / METAL / CUDA / ROCM · QWEN ON 64GB

DeepSeek V4 Flash is a large mixture-of-experts model. The usual path is remote serving; ds4 starts from the opposite constraint.

Asymmetric quantization targets the routed experts while preserving critical paths. The model becomes practical on high-memory machines.

(以上为原文节选,完整内容见下方”原文来源”)

这条动态今日登上 Hacker News 首页(88 赞 / 16 评论,来源 dwarfstar.sh)。技术雷达每日自动聚合 AI 工程、后端架构、DevOps 方向的前沿动态;相关工程落地可浏览下方的相关服务与延伸阅读,或直接与我们团队交流。