Ecosystem & Stack: cuda

vLLM is a high-throughput and memory-efficient open-source library designed for fast and easy serving of large language models.

A KVCache-centric disaggregated architecture for high-performance LLM serving, powering leading AI services.

A cross-platform desktop tool for batch generating and translating subtitles for videos and audio using various AI services and local models.

A PyTorch library enabling accessible large language models through k-bit quantization, significantly reducing memory consumption for both inference and training.

A PyTorch-based framework to adapt Meta AI's Segment Anything Model (SAM) for improved performance on challenging downstream computer vision tasks using adapters and prompts.

A deep learning toolkit for training custom multimodal large language models focused on speech, language, audio, and music processing.

A beginner-friendly UI for fine-tuning large language models (LLMs) using the LoRA method on commodity NVIDIA GPUs.

A cost-effective solution for finetuning ChatGLM-6B with LoRA, enabling personalized large language models.

A modular PyTorch library for state-of-the-art diffusion models, enabling easy inference and training for image, video, and audio generation.

An open-source, AI-driven tool for advanced image inpainting, outpainting, object removal, and replacement using state-of-the-art models.

Extends ComfyUI with advanced custom nodes for the LTX-2 video generation model, enabling powerful text-to-video and image-to-video workflows.

A fast, minimal PyTorch port of DALL·E Mini for efficient text-to-image generation.

A powerful web-based tool for few-shot voice cloning and text-to-speech, enabling high-quality voice generation from minimal audio data.

A framework for efficient, fast, and cheap serving of omni-modality (text, image, video, audio) AI models.

A toolkit for finetuning ChatGLM series models (ChatGLM-6B, ChatGLM2-6B, ChatGLM3-6B) using various methods like Freeze, Lora, P-tuning, and full parameter training for downstream NLP tasks.

An AI-powered web application for comprehensive multimedia content creation, offering speech recognition, voice cloning, text-to-speech, and multilingual translation.

Provides a local web interface and API for ChatTTS to synthesize text into speech, supporting mixed Chinese, English, and numbers.

DiffSinger is an official PyTorch implementation of a singing voice synthesis (SVS) and text-to-speech (TTS) system, leveraging a shallow diffusion mechanism for high-quality audio generation.

An open-source implementation of Microsoft's VALL-E X, enabling zero-shot multilingual text-to-speech synthesis and voice cloning with emotion control.

SD.Next is a powerful, all-in-one open-source WebUI for AI generative image and video creation, offering extensive model support, advanced processing, and cross-platform compatibility.

Create dynamic and visually captivating videos by smoothly morphing between different text prompts using Stable Diffusion.

An extensive node suite that integrates advanced 3D input processing and asset generation into ComfyUI using cutting-edge AI algorithms and models.

An open-source, theoretical reconstruction of the Claude Mythos LLM architecture, featuring a Recurrent-Depth Transformer and sparse Mixture of Experts for advanced reasoning.

Edit Banana transforms static, uneditable content like images of diagrams into fully manipulatable and editable assets using advanced AI.