Lists (2)
Stars
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Retrieval and Retrieval-augmented LLMs
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Official implementation of paper: Shallow Flow Matching for Coarse-to-Fine Text-to-Speech Synthesis
Fully automatic censorship removal for language models
Dialog2Flow: convert your dialogs to flows. This repository accompanies the paper "Dialog2Flow: Pre-training Soft-Contrastive Sentence Embeddings for Automatic Dialog Flow Extraction", accepted to …
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…
GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 training.
The official github repo for "Diffusion Language Models are Super Data Learners".
An interface library for RL post training with environments.
Samples for CUDA Developers which demonstrates features in CUDA Toolkit
My own repository containing the codes I wrote to practice CUDA programming.
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
Speed up model training by fixing data loading.
pytorch notebook for implemention for cut-cross-entropy LLM training.
A family of open-sourced Mixture-of-Experts (MoE) Large Language Models
Our library for RL environments + evals
Entropy Based Sampling and Parallel CoT Decoding
Hydra is a framework for elegantly configuring complex applications