← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

cache-dit

github.com

A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for 100+ DiTs.

Open source

Visit github.comexternal siteGitHub1,302 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. ao

    PyTorch native quantization for training and inference

    github.comOpen sourcelatest reaction

    Hacker News
    No reaction
    GitHub
    3,023 stars

  2. gemma.cpp

    lightweight, standalone C++ inference engine for Google's Gemma models.

    github.comOpen sourcelatest reaction

    Hacker News
    No reaction
    GitHub
    7,079 stars

  3. Genie-TTS

    GPT-SoVITS ONNX Inference Engine & Model Converter

    github.comOpen sourcelatest reaction

    Hacker News
    No reaction
    GitHub
    1,840 stars

  4. tokenspeed

    TokenSpeed is a speed-of-light LLM inference engine.

    github.comOpen sourcelatest reaction

    Hacker News
    No reaction
    GitHub
    2,885 stars

  5. An RDMA/Infiniband Distributed Cache for Fast Inference and Training

    A high-performance RDMA distributed file system for fast LLM Inference and GPU Training.

    github.comOpen source3 reactionslatest reaction

    Hacker News
    13 pts
    GitHub
    47 stars