Graphs that teach > graphs that impress. Turn any code, or knowledge base (Karpathy LLM wiki), into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claud…

Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.

很多镜像都在国外。比如 gcr 。国内下载很慢，需要加速。致力于提供连接全世界的稳定可靠安全的容器镜像服务。

分享AI Infra知识&代码练习：PyTorch/vLLM/SGLang框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

Public repository for Agent Skills

Give your agents the power of the Hugging Face ecosystem

KV cache store for distributed LLM inference

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice…

A generative speech model for daily dialogue.

Custom comfyui nodes for vllm-omni

Build compute kernels and load them from the Hub.

A framework for efficient model inference with omni-modality models

Heterogeneous GPU Sharing on Kubernetes

Light Image Video Generation Inference Framework

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

A repo for all spark examples using Rapids Accelerator including ETL, ML/DL, etc.

Nano vLLM

Tongyi Deep Research, the Leading Open-source Deep Research Agent

LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.

Wan: Open and Advanced Large-Scale Video Generative Models

Open-Source Frontier Voice AI

A PyTorch-native inference engine with cache, parallelism, quantization for Diffusion Transformers.

使用vllm加速cosyvoice2的推理

Serving multiple LoRA finetuned LLM as one

Utilities intended for use with Llama models.

Context engineering is the new vibe coding - it's the way to actually make AI coding assistants work. Claude Code is the best for this so that's what this repo is centered around, but you can apply…