DeepEP: an efficient expert-parallel communication library

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

MoBA: Mixture of Block Attention for Long-Context LLMs

minimal-cost for training 0.5B R1-Zero

生成扩散模型的Keras实现

Train your grpo with zero dataset and low resources, 8bit/4bit/lora/qlora supported, multi-gpu supported ...

Dense Dilated Convolutions Merging Network for Semantic Segmentation

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

PyTorch implementation of DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (focused on DiffSpeech)

Use PEFT or Full-parameter to finetune 450+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, I…

Fully open data curation for reasoning models

The easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.

[arXiv 2024] Generalizable Humanoid Manipulation with 3D Diffusion Policies. Part 1: Train & Deploy of iDP3

[RSS 2024] 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations

Fully open reproduction of DeepSeek-R1

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

verl: Volcano Engine Reinforcement Learning for LLMs

Janus-Series: Unified Multimodal Understanding and Generation Models

Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch

Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"

Stanford NLP Python library for Representation Finetuning (ReFT)

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Unofficial implementation of "Simplifying, Stabilizing & Scaling Continuous-Time Consistency Models" for MNIST

An Open Large Reasoning Model for Real-World Solutions