Bundle
@raullenchai/dsh-provider
Native Rapid-MLX provider for DeepSeek Harness — teaches DSH what the local server already knows (memory-fitted context via max_model_len), plus model-management tools and a /rapid-mlx overview.
raullenchai71
3 results
Native Rapid-MLX provider for DeepSeek Harness — teaches DSH what the local server already knows (memory-fitted context via max_model_len), plus model-management tools and a /rapid-mlx overview.
在 Apple Silicon 上用 MLX 框架运行本地大模型:模型目录管理、服务启停、OpenAI 兼容 API,并优化 DSH 自定义提供方的本地思考强度选择。
DeepSeek Harness plugin for local MLX-LM and MLX-VLM models with loopback-only defaults, managed startup, and a macOS Desktop PTY compatibility provider