由于 trendforge.devlive.top 访问受限,请切换到 trendforge.devlive.org 域名
inference
话题找到数量
ddalcu/mlx-serve
专为Apple Silicon打造的原生LLM推理服务器,兼容OpenAI与Anthropic API,无需Python环境。包含基于MLX Core的macOS应用,支持聊天、智能体模式及工具调用功能。
neuron-core/neuron-ai
PHP 生态系统的代理框架,用于构建生产就绪的人工智能驱动的应用程序。将组件(LLM、工具、矢量 DB、内存)连接到与数据和 UI 交互的代理。
youssofal/MTPLX
MLX 速度提高 3 倍 |酷文3.8 27B | Apple Silicon 上的本机 MTP 推测解码,无需外部起草器。
pedrohcgs/claude-code-my-workflow
面向使用LaTeX/Beamer与R的学术工作者可即时复用的Claude代码模板,包含多智能体审阅、质量门控、对抗性质量检查及复现协议。
AtomicBot-ai/Atomic-Chat
Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https://discord.com/invite/8wGSsvmg4V
jax-ml/scaling-book
“How To Scale Your Model”的主页,这是一本关于在 TPU 上扩展法学硕士的简短博客式教科书
theopenco/llmgateway
Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.
carloslfu/slotstream
Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB Apple Silicon Macs. Fully native Swift, MLX and Metal. Offline, no Python. CLI, Swift library, and Ollama/OpenAI/Anthropic APIs. Works with Claude Code and Codex.
smg-project/smg
Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing, chat history, tokenization caching, Responses API, embeddings, WASM plugins, MCP, and multi-tenant auth.