AIAny - pytorch

DiffSynth-Studio

2023

ModelScope Community, Artiprocher

DiffSynth-Studio is an open-source Diffusion model engine developed and maintained by the ModelScope Community, focusing on image and video generation. It supports mainstream models like FLUX, Wan, and Qwen-Image, offering efficient memory management and flexible training frameworks. Key features include VRAM optimization, low-memory inference, LoRA/ControlNet training, and innovative techniques like EliGen and Nexus-Gen for pushing generative model boundaries.

github AIGC ai-tools ai-image ai-video+5

torchtitan

2023

PyTorch

torchtitan is a PyTorch-native platform for rapid experimentation and large-scale training of generative AI models. It provides multi-dimensional composable parallelisms (FSDP2, tensor/pipeline/context parallel), distributed checkpointing, float8 and MXFP8 support, torch.compile integration, and out-of-the-box support for training Llama 3.1 models. It targets both research and production-scale LLM pretraining.

pytorch ai-train llm foundation-model ai-library+2

Flash Linear Attention

2023

fla-org, Songlin Yang +1

Flash Linear Attention (fla) is a Triton- and PyTorch-based library providing efficient implementations of state-of-the-art linear attention mechanisms and related modules. It targets hardware-efficient kernels, supports multiple platforms (NVIDIA, AMD, Intel), and provides models and utilities compatible with Hugging Face Transformers for training and inference.

pytorch github ai-library llm huggingface+1

LLM Transparency Tool

2023

facebookresearch, Igor Tufanov +3

LLM Transparency Tool (LLM-TT) is an open-source interactive toolkit from Facebook Research for analyzing the internal workings of Transformer-based language models. It lets users run inferences, explore contribution graphs tied to selected tokens, inspect representations after any block, and drill down to attention heads, FFN blocks and individual neurons to see how they promote or suppress output tokens. The project provides Docker and local installation instructions and a live demo hosted on Hugging Face.

github llm NLP xai ai-tools+3

GPT-SoVITS-WebUI

2024

RVC-Boss

GPT-SoVITS-WebUI is an open-source few-shot voice conversion and text-to-speech WebUI. It supports zero-shot (5s) TTS, few-shot (1min) fine-tuning for voice cloning, cross-lingual synthesis, integrated tooling (vocal separation, dataset slicing, ASR, text labeling) and multiple pretrained model versions (v1–v4, v2Pro, etc.).

github audio pytorch ASR huggingface+3

Stable Diffusion WebUI Forge

2024

lllyasviel

Stable Diffusion WebUI Forge (Forge) is a platform built on top of AUTOMATIC1111's Stable Diffusion WebUI (Gradio-based). It aims to make development easier, optimize GPU/memory resource management, speed up inference, and provide experimental integrations and features. Forge includes one-click installers for preconfigured CUDA/PyTorch environments, native support for low-bit formats (GGUF, NF4, BitsAndBytes), LoRA handling, GPU weight/swapping controls, integrated extensions (e.g. FreeU, Unet patches, enhanced Gradio 4 canvas), and a compatibility/status tracking table.

github ai-image ai-tools pytorch ai-inference+1

FastVideo

2024

The FastVideo Team, hao-ai-lab

FastVideo is a unified post-training and inference framework for accelerated video generation. It supports end-to-end pipelines for diffusion models, from data preprocessing to training, finetuning, distillation, and inference. Key features include sparse distillation for over 50x denoising speedup, optimizations like Video Sparse Attention, and support for various hardware and OS.

github ai-video pytorch huggingface ai-tools+3

TimesFM

2024

Google Research

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model from Google Research for forecasting. The GitHub repo provides model code, installation instructions, inference examples (PyTorch and Flax), links to checkpoints (Hugging Face), and notes about integration with BigQuery and model versions (e.g., TimesFM 2.5).

foundation-model google pytorch huggingface ai-train+4

LMCache

2024

LMCache

LMCache is an open-source, high-performance KV (key-value) cache layer designed to accelerate LLM serving and inference, especially for long-context scenarios. By storing and reusing KV caches across GPU, CPU DRAM and local disk, and enabling cross-instance sharing, LMCache reduces time-to-first-token (TTFT) and GPU usage. It integrates tightly with vLLM, supports P2P cache sharing, non-prefix caches, multiple storage backends (CPU, disk, NIXL), and is distributed under Apache-2.0.

LLM llm ai-serving ai-inference ai-library+4

Hands-On Large Language Models

2024

Jay Alammar, Maarten Grootendorst +1

Official code repository for the O'Reilly book "Hands-On Large Language Models" by Jay Alammar and Maarten Grootendorst. It provides runnable notebooks, visual explanations, and practical examples across chapters covering tokens and embeddings, transformer internals, text classification, semantic search, fine-tuning, multimodal models, and more. Recommended to run in Google Colab for easy setup.

book llm LLM github tutorial+5

CosyVoice (Fun-CosyVoice)

2024

FunAudioLLM

CosyVoice (Fun-CosyVoice) is a multilingual, LLM-based text-to-speech (TTS) system that provides end-to-end capabilities for training, inference and deployment. It focuses on zero-shot voice cloning, strong content consistency, speaker similarity and natural prosody, supports many languages and Chinese dialects, pronunciation inpainting, text normalization, and low-latency bi-streaming for production use.

audio LLM huggingface pytorch ai-inference+2

MiniMind-V

2024

Jingyao Gong (jingyaogong)

MiniMind-V is an open-source tiny visual-language model (VLM) project that demonstrates how to train a 26M-parameter multimodal VLM from scratch quickly and cheaply (example: ~1 hour / single 3090 GPU and very low rental cost). The repo provides end-to-end code for data cleaning, pretraining, supervised fine-tuning (SFT), evaluation and demo, using CLIP as the visual encoder and MiniMind as the base LLM.

vision pytorch github llm ai-train+2

Tag

Explore by tags

All

30u30

ASR

ChatGPT

GNN

IDE

RAG

ai-agent

ai-api

ai-api-management

ai-client

ai-coding

ai-demos

ai-development

ai-framework

ai-image

ai-image-demos

ai-inference

ai-leaderboard

ai-library

ai-rank

ai-serving

ai-tools

ai-train

ai-video

ai-workflow

AIGC

alibaba

amazon

anthropic

audio

blog

book

bytedance

chatbot

chemistry

claude

course

deepmind

deepseek

engineering

foundation

foundation-model

gemini

github

google

gradient-booting

grok

huggingface

LLM

llm

math

mcp

mcp-client

mcp-server

meta-ai

microsoft

mlops

NLP

nvidia

ocr

ollama

openai

paper

physics

plugin

pytorch

RL

science

sora

translation

tutorial

vibe-coding

video

vision

xAI

xai

DiffSynth-Studio