Skip to content
View ujay-zheng's full-sized avatar
  • USTC
  • HeiFei/JinHua

Block or report ujay-zheng

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Starred repositories

Showing results

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

Rust 185,109 108,397 Updated Apr 16, 2026

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

Python 2,597 315 Updated Apr 9, 2026

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

Python 76,905 15,682 Updated Apr 16, 2026

Paper reading and discussion notes, covering AI frameworks, distributed systems, cluster management, etc.

59 1 Updated Mar 4, 2026

Contexts Optical Compression

Python 22,836 2,103 Updated Jan 27, 2026
Python 26 4 Updated Apr 8, 2026

Boosting GPU utilization for LLM serving via dynamic spatial-temporal prefill & decode orchestration

Python 43 7 Updated Jan 8, 2026

Dynamic Memory Management for Serving LLMs without PagedAttention

C 477 41 Updated May 30, 2025

A low-latency & high-throughput serving engine for LLMs

Python 491 63 Updated Jan 8, 2026

A multi-voice TTS system trained with an emphasis on quality

Jupyter Notebook 14,844 2,050 Updated Nov 19, 2024

An official implementation for "X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval"

Python 182 20 Updated Apr 6, 2024

Zero-Shot Detection via Vision and Language Knowledge Distillation

Python 8 Updated Mar 11, 2022

[ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

Python 421 18 Updated Apr 25, 2025

[arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation

Jupyter Notebook 96 3 Updated Mar 1, 2025

Official inference code and LongText-Bench benchmark for our paper X-Omni (https://arxiv.org/pdf/2507.22058).

Python 424 11 Updated Aug 26, 2025

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Python 22,092 2,698 Updated Jan 23, 2026

X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages

Python 316 18 Updated Aug 10, 2023
Python 49 5 Updated Jul 30, 2025

Contrastive Language-Audio Pretraining

Python 2,111 213 Updated May 15, 2025

[WACV 2023] Audio-Visual Efficient Conformer (AVEC) for Robust Speech Recognition

Jupyter Notebook 101 10 Updated Feb 21, 2023

Grounded Language-Image Pre-training

Python 2,587 216 Updated Jan 24, 2024
Python 1,047 137 Updated Oct 3, 2022

An up-to-date list of works on Multi-Task Learning

378 28 Updated Mar 2, 2026

awesome-autonomous-driving

1,120 103 Updated Aug 19, 2024

Official implementation of CrossViT. https://arxiv.org/abs/2103.14899

Python 416 55 Updated Jan 12, 2022

Artifact from "Hardware Compute Partitioning on NVIDIA GPUs". THIS IS A FORK OF BAKITAS REPO. I AM NOT ONE OF THE AUTHORS OF THE PAPER.

C 59 5 Updated Nov 24, 2025

Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS

C++ 33 1 Updated Feb 10, 2025

Official Pytorch implementations for "SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation" (NeurIPS 2022)

Python 876 92 Updated Nov 22, 2022

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Jupyter Notebook 33,204 3,980 Updated Mar 25, 2026
Next