One-click Qwen3.6-27B inference on Windows. 158 tok/s on RTX 5090, 72 tok/s on RTX 3090. Native, no WSL, no Docker, no telemetry.

Qwen3.6-27B on dual RTX 3090 — TP=2 recipe, vLLM nightly, MTP + fp8 KV, validated for concurrent serving

Gradio UI for YuE

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

Code for fine-tuning GPT-J LoRAs in 4bit

Cataclysm - Code generation library for the end game

Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

Multi-GPU setup for inference with GPT NeoX 20B and OPT-30B models in huggingface

GIMP plugin for AUTOMATIC1111's Stable Diffusion WebUI

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]

graph-bot-dialog

Lightweight version of mxnet neural art implementation

Neural Artistic Style in Python

Torch implementation of neural style algorithm

A fork of Sebastian Nowozin's and Koji Tsuda's gboost code

Stanford Network Analysis Platform (SNAP) is a general purpose network analysis and graph mining library.

GraMi is a novel framework for frequent subgraph mining in a single large graph, GraMi outperforms existing techniques by 2 orders of magnitudes. GraMi supports finding frequent subgraphs as well a…

Caffe: a fast open framework for deep learning.