Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
Welcome to Leeroopedia
Your ML & Data Knowledge Wiki. Best practices and expert-level knowledge for Machine Learning and Data Engineering, covering 1000+ frameworks and libraries from training to deployment.
Browse implementation patterns, configuration guides, debugging heuristics, and battle-tested defaults for frameworks like vLLM, DeepSpeed, Megatron-LM, FlashAttention, Triton, Unsloth, LangChain, and many more. Every page is structured so both humans and AI agents can find what they need fast.
Connect your AI coding agent. Plug Leeroopedia into your favorite coding agent, and let it build robust AI/ML systems autonomously:
- SuperML plugin — converts your AI coding agent into an expert ML engineer with agentic memory
- Leeroopedia MCP — search over best-practices and skills of ML/AI
- Kapso — experimentation platform for autonomous AI/ML software building
Browse by Category
| Category | Description | Browse |
|---|---|---|
| Workflows | Step-by-step processes and procedures | Browse All |
| Principles | Core ideas and foundational knowledge | Browse All |
| Implementations | Code-level details and modules | Browse All |
| Heuristics | Best practices and guidelines | Browse All |
| Environments | Setup and configuration guides | Browse All |
Explore Pages
Workflows
- Workflow:Getgauge Taiko Headless Browser Testing
- Workflow:Microsoft Autogen Studio Team Deployment
- Workflow:Neuml Txtai RAG Pipeline
- Workflow:Duckdb Duckdb Extension Development And Distribution
- Workflow:Shiyu coder Kronos CSV Finetuning
- Workflow:VainF Torch Pruning Sparse Training Pruning
- Workflow:Facebookresearch Habitat lab PointNav PPO Training
- Workflow:Google deepmind Dm control Multi Agent Soccer Setup
- Workflow:Mbzuai oryx Awesome LLM Post training Deep Paper Collection
- Workflow:Axolotl ai cloud Axolotl DPO Preference Alignment
Principles
- Principle:Alibaba ROLL Environment Management
- Principle:Protectai Llm guard Malicious URL Detection
- Principle:Sktime Pytorch forecasting NHiTS Architecture
- Principle:Langfuse Langfuse Data Streaming from ClickHouse
- Principle:Heibaiying BigData Notes Spark Data Loading
- Principle:LaurentMazare Tch rs C FFI Bridge
- Principle:Avdvg InjectGuard Similarity Search Detection
- Principle:Arize ai Phoenix Annotation Analysis
- Principle:Duckdb Duckdb FSST String Compression
- Principle:Huggingface Diffusers Package Distribution
Implementations
- Implementation:Heibaiying BigData Notes StreamExecutionEnvironment Execute
- Implementation:Predibase Lorax Flash NeoX Modeling
- Implementation:Speechbrain Speechbrain Prepare Switchboard Tokenizer
- Implementation:Facebookresearch Audiocraft NormConv
- Implementation:Microsoft LoRA Lora State Dict
- Implementation:Deepspeedai DeepSpeed XPU Packbits
- Implementation:Webdriverio Webdriverio PIteration
- Implementation:Elevenlabs Elevenlabs python DubbingMetadataResponse
- Implementation:Microsoft Playwright CrInput
- Implementation:OpenHands OpenHands Tooltip
Heuristics
- Heuristic:Helicone Helicone Anthropic Cache Double Count Prevention
- Heuristic:ThreeSR Awesome Inference Time Scaling API Rate Limiting Tip
- Heuristic:ChenghaoMou Text dedup Fingerprint Batch Size One
- Heuristic:Apache Kafka JVM GC Tuning Defaults
- Heuristic:Iterative Dvc Path Performance Optimization
- Heuristic:Google research Deduplicate text datasets Parallel Job Scaling By Data Size
- Heuristic:LMCache LMCache CacheGen Quantization Strategy
- Heuristic:Zai org CogVideo Data Preparation Best Practices
- Heuristic:Openai Openai node Retry Backoff Configuration
- Heuristic:DataExpert io Data engineer handbook SparkSession Singleton Pattern
Environments
- Environment:Mlflow Mlflow MLflow Server Environment
- Environment:Anthropics Anthropic sdk python GCP Vertex Environment
- Environment:Wandb Weave LLM Integration Dependencies
- Environment:Webdriverio Webdriverio Cloud Service Credentials
- Environment:Intel Ipex llm NPU Cpp Environment
- Environment:Rapidsai Cuml Python RAPIDS Stack
- Environment:Hpcaitech ColossalAI CUDA GPU Environment
- Environment:Lance format Lance Rust Toolchain
- Environment:Openclaw Openclaw Docker Deployment Environment
- Environment:Mbzuai oryx Awesome LLM Post training Python Matplotlib