TokenSpeed is a speed-of-light LLM inference engine.
Repository Index
132,241 visible repositories in the index
25–48 of 58 · Most stars
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
- apple-silicon
- local-ai
- mlx
- mtp
🎬 Evidence-led Seedance 2.5 / 2.0 prompt library: 1000+ cases traced to original posts, 490+ cross-model retest runs, 27 copy-ready templates, 80+ installable AI-video Skills. Synced daily from goodcase.ai. EN / 中文 / 日本語.
- ai-video
- awesome
- bytedance
- prompt-engineering
MiniMax-M2, a model built for Max coding & agentic workflows.
和国产大模型相关的免费工具集
- claude
- glm
- kimi-k2
- minimax
A simple, performant, and scalable Jax LLM!
OpenAI 接口接入适配,支持千帆大模型平台、讯飞星火大模型、腾讯混元以及MiniMax、Deep-Seek,等兼容OpenAI接口,仅单可执行文件,配置超级简单,一键部署,开箱即用. Seamlessly integrate with OpenAI and compatible APIs using a single executable for quick setup and deployment.
Use Claude and Antigravity with Pi, OpenCode and other coding clients. Local API bridge, usage dashboard and Mac app. Antigravity preview available in 1.74.0.
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.
A robust Python tool for text-based AI training and generation using GPT-2.
Chat2API enables zero-cost access to leading AI models by leveraging official web UIs. It supports providers such as DeepSeek, GLM, Kimi, MiniMax, Qwen, and Z.ai, and seamlessly integrates with tools like openlcaw, Cline, and Roo-Code.
- chatgpt-api
- deepseek-chat
- free-api
- glm-5
[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow *TriggerFlow* to manage complex GenAI working logic 🔀 Switch to any model without rewrite application code
- agent
- agent-framework
- python
- framework
Multimodal RL training framework for diffusion & omni models
- diffusion-models
- flow-matching
- grpo
- multimodal
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
The repository host gives no description.
The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with maximum 200+ tok/s single-request decode with support of FP8 weight ( Join Discord :https://discord.gg/VFqVVySdMS )
Prompt chains maximize intelligence and results when using LLMs
A simple tool to select files from a repository to copy/paste into an LLM
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
- llm
- vlm
- finetuning
- gemma3
maxxing the ability to run different LLMs on the smallest devices possible
🤖 24/7 AI agent that maximizes Claude Code Pro usage via Slack. Auto-processes tasks, manages isolated workspaces, creates Git commits/PRs, and optimizes day/night usage thresholds.
- ai-agent
- anthropic
- automation
- python
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
- apple-silicon
- clover
- coding-agents
- decision-models
Command Code API 反代代理,兼容 OpenAI 与 Anthropic 接口 | Reverse proxy exposing Command Code API as OpenAI- and Anthropic-compatible endpoints
Fizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Anima & Z-Image Turbo and Ace-Step XL: train, fine-tune, profile, repair and extract LoRAs & LoKR for Image, Video & Music Models
- ai
- deep-learning
- flux
- generative-ai