8000 TKONIY (Yangshen Deng) / Starred · GitHub
[go: up one dir, main page]

Skip to content
View TKONIY's full-sized avatar
🌋
Working on Data x AI
🌋
Working on Data x AI

Organizations

@DBGroup-SUSTech

Block or report TKONIY

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

Starred repositories

Showing results

Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.

Go 13,391 1,241 Updated Nov 21, 2026

Modular open-source sEMG hardware (2ch/8ch/16ch KiCad & EasyEDA Pro), firmware, and studio

Python 18 2 Updated Nov 21, 2026

DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers

Cuda 550 81 Updated Sep 30, 2026

EAT: Evolving Agent Teams (NeurIPS'26). A supervisor agent evolves teams of coding agents for long-running optimization tasks.

Shell 133 8 Updated Nov 10, 2026

Accurate, fast FP4 KV-cache decoding through algorithm-system co-design.

Python 57 5 Updated Nov 9, 2026

Fast, exact fused top-k selection for learned sparse attention training and inference, from HyScale (Tencent Hy & University of Edinburgh).

Python 58 12 Updated Nov 9, 2026

Code World Model Official Repo

Python 589 22 Updated Aug 27, 2026

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

Python 1,398 154 Updated Nov 21, 2026

Infrastructure for continually self‑improving agents

Python 7,650 731 Updated Nov 21, 2026

Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code…

PowerShell 45,041 6,729 Updated Nov 14, 2026

DeepSeek Harness: Everything is a Plugin.

TypeScript 285,092 35,440 Updated Nov 18, 2026

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

TypeScript 123,196 15,891 Updated Nov 21, 2026

Mixture-of-experts (MoE) training megakernel for NVL72s

Python 648 90 Updated Oct 1, 2026

Infinite Worlds with Versatile Interactions

Python 1,914 151 Updated Sep 10, 2026

KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels

Python 54 AE94 1 Updated Jun 1, 2026

Paper list of multi-agent reinforcement learning (MARL)

4,896 770 Updated Feb 11, 2026
Cuda 20 1 Updated Nov 14, 2026

MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts

Python 1,216 153 Updated Oct 12, 2026

Reference implementation and examples of the CuTe Layout representation and algebra.

Python 398 44 Updated Nov 3, 2026

AgentENV (AENV) is a distributed platform for running agent environments at scale.

Rust 3,775 375 Updated Nov 20, 2026

Companion code for the global workspace interpretability paper

Python 2,195 317 Updated Oct 10, 2026

FlashMLA: Efficient Multi-head Latent Attention Kernels

C++ 13,275 1,282 Updated Oct 27, 2026

TokenSpeed is a speed-of-light LLM inference engine.

Python 2,944 424 Updated Nov 21, 2026

Kernels, of the mega variety :)

Python 886 71 Updated May 26, 2026

A high-performance, universal serving framework for any-to-any models.

Python 117 50 Updated Nov 18, 2026

A copy of the Cursor AI editor theme from cursor.sh, repackaged for use in Visual Studio Code without needing the Cursor editor.

37 6 Updated Sep 17, 2025

High-Throughput Batch Inference

C++ 22 1 Updated Nov 20, 2026

Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"

Python 269 15 Updated Sep 12, 2025

ElasticMM: Elastic and Efficient MLLM Serving System

Python 43 2 Updated May 10, 2026
Next
0