Chien Nguyen Claim this profile

Fast, lossless LLM inference via dual-view diffusion decoding.

Evoluationay Algorithms Project: Learning-Based Queuing Delay-Aware Task Offloading in Collaborative Vehicular Networks

Label-Representative Graph Convolutional Network for Multi-Label Text Classification

Question Answering Interactive System

This repository is the official implementation of our paper.

OpenChat: Less is More for Open-source Models

No description.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Utilities for Training Very Large Models

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.