Skip to content
View JunnYu's full-sized avatar
🐢
Focusing
🐢
Focusing

Organizations

@PaddlePaddle

Block or report JunnYu

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. 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
Showing results

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…

Python 11,399 1,908 Updated Nov 17, 2026

DeepSeek Harness: Everything is a Plugin.

TypeScript 282,723 35,033 Updated Nov 13, 2026

MAGI-2-preview: Scaling Video Generation Models Efficiently

Python 658 21 Updated Aug 6, 2026

A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).

Python 1,360 151 Updated Nov 17, 2026

Uni-Agent is a framework for training long-horizon agents.

Python 732 158 Updated Nov 17, 2026

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

Python 3,329 628 Updated Nov 17, 2026

Build compute kernels and load them from the Hub.

Python 790 149 Updated Nov 17, 2026

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

JavaScript 304,947 44,907 Updated Nov 17, 2026

An asynchronous streaming data management module for efficient post-training.

Python 175 58 Updated Nov 13, 2026

A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL workflows

Python 179 23 Updated Oct 19, 2026

Contexts Optical Compression

Python 24,174 2,216 Updated Jan 27, 2026

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

Python 10,859 1,013 Updated Nov 16, 2026

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

Python 3,454 330 Updated Nov 17, 2026

Agentic RL Training at Scale

Python 2,251 502 Updated Nov 17, 2026

A PyTorch native platform for training generative AI models

Python 5,916 1,085 Updated Nov 17, 2026

诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

11,552 1,280 Updated Jul 9, 2025

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Python 92,794 11,657 Updated Sep 16, 2026

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

Python 5,914 662 Updated Nov 17, 2026

Unleashing the Power of Reinforcement Learning for Math and Code Reasoners

Python 740 44 Updated Jun 6, 2025

Distributed Compiler and Optimized Parallel Kernels

Python 1,580 177 Updated Sep 18, 2026

FlashInfer: Kernel Library for LLM Serving

Cuda 6,948 1,765 Updated Nov 17, 2026

A dict[str, torch.Tensor] that behaves like one tensor, and TensorClass: typed, batched dataclasses that compile.

Python 1,046 155 Updated Nov 17, 2026

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

C++ 10,474 1,158 Updated Nov 8, 2026

A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.

Python 3,035 343 Updated Jan 14, 2026

DeepGEMM: clean and efficient BLAS kernel library on GPU

Cuda 9,201 1,533 Updated Oct 20, 2026

DeepEP: an efficient expert-parallel communication library

Cuda 10,449 1,562 Updated Oct 21, 2026

FlashMLA: Efficient Multi-head Latent Attention Kernels

C++ 13,275 1,278 Updated Oct 27, 2026

Official Repo for Open-Reasoner-Zero

Python 2,102 120 Updated Jun 2, 2025

A stand-alone implementation of several NumPy dtype extensions used in machine learning.

C++ 371 71 Updated Nov 16, 2026

Solve Visual Understanding with Reinforced VLMs

Python 6,047 384 Updated Jul 7, 2026
Next