ai-agent

llm-algo-leetcode – Master LLM Algorithms with Hands‑On Notebooks

A Jupyter‑based lab that blends theory, solutions, and test cases, helping founders and engineers quickly level up from LLM basics to advanced CUDA/Triton implementations.

From the repo · “LLM algorithm practice lab with theory, solutions, and test cases.《大模型算法实战教程》面向大模型入门到进阶的算法实战教程,覆盖原理讲解、答案解析、测试用例与 CUDA/Triton 实战。”

708 stars+21★ this week147 forksJupyter NotebookGuide quality 8/10 · reviewed Oct 10Updated 10/22/2026100% free · open source
What it does

The llm-algo-leetcode tool provides a practice lab for startup founders to learn and implement large language model algorithms with theory, solutions, and test cases, including CUDA and Triton.

When to use it
  • •When you need to improve your understanding of large language model algorithms
  • •When you want to practice implementing algorithms with real test cases
  • •When you need a resource to learn CUDA and Triton for large language model development
Ready-to-paste prompt
Run the `llm_algo_leetcode.ipynb` Jupyter Notebook to start the practice lab and explore the large language model algorithms
Heads up: Make sure you have the necessary dependencies installed, including Jupyter Notebook, and a compatible CUDA and Triton environment to run the GPU-accelerated examples
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/llm-algo-leetcode && curl -fsSL https://workflowstacks.com/api/skills/llm-algo-leetcode/claude-skill -o ~/.claude/skills/llm-algo-leetcode/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How llm-algo-leetcode – Master LLM Algorithms with Hands‑On Notebooks works
Codeflow
Free to inspect

Llm-algo-leetcode – Master LLM Algorithms with Hands‑On Notebooks is mostly documents (746 doc files, 102 small scripts) — something you read, not something you run. There is nothing to install. Last commit this month, Other license.

Size
Mostly documents
746 documents · 102 small scripts · days to read — use, don't read
Setup
Nothing to install
A course / notebook collection. Read it; run cells if you like.
Runs on
Nowhere — you read it
A reading resource, not a program.
Jupyter Notebook 87%Python 13%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
What's in each folder
docs/Documentation1046 files
topic_discussion/Folder184 files
benchmarks/Evaluations & benchmarks147 files
02_PyTorch_Algorithms/Folder139 files
tools/Helper scripts112 files
requirements/Folder32 files
00_Prerequisites/Folder26 files
READMEHas testsDocumentedCI checksOther licenseUpdated this month
Quick Actions
Details
Creator
datawhalechina
Language
Jupyter Notebook
Category
ai-agent
Published
4/1/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/llm-algo-leetcode.svg)](https://workflowstacks.com/skills/llm-algo-leetcode?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.