This project aims to build a reusable, scalable, and composable verl-GR framework based on verl to uniformly support post-training requirements for different GR paths.

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

Code of DL-DRL

为原始的pytorch-drl4vrp代码添加注释和bug修复

Deep Reinforcement Learning for Multiobjective Optimization. Code for this paper

An Open Foundation Model and Benchmark to Accelerate Generative Recommendation

Adding ring-attn to vllm-omni

A framework for efficient model inference with omni-modality models

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Using transformer for time series forecasting

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference

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

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

This is an implementation for MQ-AttnSAS and MQ-AttnS3

🤗 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.

one for all, Optimal generator with No Exception

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

推荐系统入门教程，在线阅读地址：https://datawhalechina.github.io/fun-rec/

D-VAE: A Variational Autoencoder for Directed Acyclic Graphs, NeurIPS 2019

Code for Findings-ACL 2023 paper: Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence

Simple and Efficient Tensorflow implementations of NER models with tf.estimator and tf.data

A JavaFX data visualization project