hyperai/tvm-cn

TVM Documentation in Chinese Simplified / TVM 中文文档

Project: hyperai/tvm-cn

This project is a Chinese-language documentation site for Apache TVM, an open-source deep learning compiler that works across hardware like CPU, GPU, and ARM. The goal is to make TVM easier to learn for Chinese-speaking developers by providing a centralized, up-to-date translation of the official TVM docs.

The current Chinese docs are based on TVM version v0.10.0 and are built with Docusaurus, a static site generator. The README explains how to set up a local development server (requires Node.js and pnpm), how to migrate external images into the project, and how to create new versioned docs when TVM releases updates.

Contributors are welcome to:

  • Report translation issues or submit pull requests
  • Help translate and maintain the docs
  • Join the Chinese TVM community for discussion

The project also provides a link to the live Chinese documentation site and a contribution guide.

In short, it’s a community-driven effort to make TVM’s documentation accessible in Chinese, with clear instructions for anyone who wants to help improve it.

Related

  • Project
    vllm-project/llm-compressor

    LLM Compressor is a Python library that quantizes and compresses large language models for fast, low‑memory inference with vLLM. It supports many low‑bit formats (FP8, FP4, INT4), a variety of algorithms (GPTQ, AWQ, AutoRound, REAP), and can handle multi‑trillion‑parameter models via disk off‑loading and DDP. The library integrates directly with Hugging Face checkpoints, saves models in the `compressed‑tensors` format, and provides ready‑to‑use examples and pre‑compressed checkpoints.

  • Project
    NVIDIA/k8s-device-plugin

    The NVIDIA k8s‑device‑plugin is an official DaemonSet that implements Kubernetes’ device‑plugin API for NVIDIA GPUs. It discovers GPUs, reports health, and makes them schedulable via the `nvidia.com/gpu` resource (with optional MIG and shared‑GPU modes). Install the NVIDIA driver and container toolkit on each node, deploy the plugin (static manifest or Helm), then request GPUs in pod specs. Configuration is possible via flags, env‑vars, or a YAML file, covering MIG strategy, device‑list delivery, shared‑GPU (time‑slicing or MPS), and more. The plugin is beta, lacks full health‑check/cleanup, and only the official NVIDIA version is supported.

  • Project
    Lightning-AI/LitServe

    LitServe is a Python-based framework for building custom inference servers, allowing developers to define their own logic for batching, routing, and orchestration for models, agents, and RAG pipelines.

  • Project
    nunchux-ai/nunchaku

    A high-performance inference engine that uses SVDQuant to enable 4-bit quantization for diffusion models, significantly reducing VRAM usage and increasing inference speed.