Skip to content
View zky001's full-sized avatar
  • tsinghua
  • 10:14 (UTC -12:00)

Highlights

  • Pro

Block or report zky001

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

墨记 Inkmark — 所见即所得的 Markdown 编辑器,一套内核三种形态:桌面版 / 网页版 / PWA

JavaScript 2 1 Updated Aug 10, 2026

匿名水印聊天室+模型匿名评测平台

JavaScript 1 Updated Jul 17, 2026

大模型是怎么炼成的——从预测下一个词到 RLHF,人人都能看懂的大模型训练交互式图解教程

TypeScript 3 Updated Aug 27, 2026

An agent-capability evaluation platform for OpenAI-compatible LLM APIs: parameterized mock-environment tasks, deterministic state-based scoring, fair single-harness comparison, full trajectory replay.

Python 1 Updated Aug 11, 2026
Python 1 Updated Aug 14, 2026

所有小初高、大学PDF教材。

84,862 19,302 Updated Oct 26, 2026

Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed…

Python 9,667 902 Updated Nov 21, 2026

🧠 两小时从 0 训出你的 64M 大模型。Train your own 64M LLM from scratch in 2 hours.

Python 68,112 8,902 Updated Nov 21, 2026

Wan: Open and Advanced Large-Scale Video Generative Models

Python 17,473 4,086 Updated Mar 5, 2026

No fortress, purely open ground. OpenManus is Coming.

Python 59,004 10,227 Updated Nov 2, 2026

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

C++ 10,493 1,162 Updated Nov 17, 2026

A lightweight data processing framework built on DuckDB and 3FS.

Python 5,034 459 Updated Mar 5, 2025

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

Python 3,036 344 Updated Jan 14, 2026

DeepGEMM: clean and efficient BLAS kernel library on GPU

Cuda 9,212 1,540 Updated Nov 19, 2026

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

8,140 306 Updated May 15, 2025

DeepEP: an efficient expert-parallel communication library

Cuda 10,464 1,566 Updated Nov 20, 2026

FlashMLA: Efficient Multi-head Latent Attention Kernels

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

the LLM vulnerability scanner

Python 10,124 1,503 Updated Nov 18, 2026
Python 1 Updated Nov 15, 2024

flip test on glm

Python 1 Updated Oct 28, 2024
Python 1 Updated Jun 22, 2024
Python 1 Updated Jun 18, 2024
Python 1 Updated Jun 16, 2024

LLM&VLM Tutorial

Python 1,983 1,447 Updated Apr 22, 2026

LLM training in simple, raw C/CUDA

Cuda 31,520 3,834 Updated Jun 26, 2025

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Python 76,173 9,383 Updated Nov 21, 2026

[ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Python 131 15 Updated Mar 26, 2024
Next