PyTorch

ComfyUI

+1.8k

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

vllm

+638

A high-throughput and memory-efficient inference and serving engine for LLMs

laya

+580

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

reasoning-from-scratch

+265

Implement a reasoning LLM in PyTorch from scratch, step by step

OpenBMB/VoxCPM

+851

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

transformers

+293

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Soup

+202

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

ultralytics

+191

Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

phantom-kv

+92

Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.