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:FlagOpen FlagEmbedding Embedder Inference
- Workflow:Avhz RustQuant Yield Curve Construction
- Workflow:FlagOpen FlagEmbedding Reranker Inference
- Workflow:Openai CLIP Zero shot image classification
- Workflow:Mlc ai Web llm Function Calling
- Workflow:Huggingface Alignment handbook QLoRA Single GPU Finetuning
- Workflow:Openai Evals Running a single eval
- Workflow:Nightwatchjs Nightwatch Component Testing
- Workflow:Openclaw Openclaw Docker Deployment
- Workflow:Deepseek ai Janus Autoregressive Image Generation
Principles
- Principle:Deepset ai Haystack Pipeline Orchestration
- Principle:Alibaba MNN Operator Fusion Codegen
- Principle:Google deepmind Mujoco Pipeline Architecture
- Principle:Langchain ai Langchain Standard Integration Testing
- Principle:Nautechsystems Nautilus trader Code Quality Gating
- Principle:CarperAI Trlx Online RL Training
- Principle:NVIDIA NeMo Curator Video Ingestion
- Principle:Togethercomputer Together python Image Response Processing
- Principle:Ollama Ollama MLXRunner Architecture
- Principle:Ggml org Ggml Computation Graph Construction
Implementations
- Implementation:Guardrails ai Guardrails Structured Data Utils
- Implementation:Lm sys FastChat Build Side By Side Vision Anony UI
- Implementation:Norrrrrrr lyn WAInjectBench AdamW Training Loop
- Implementation:Mlc ai Web llm Function Calling Model Ids
- Implementation:Openai Openai agents python RunResultStreaming
- Implementation:Scikit learn Scikit learn FetchLfw
- Implementation:Pyro ppl Pyro TraceTMC ELBO
- Implementation:Protectai Modelscan Issues Group By Severity
- Implementation:Ggml org Llama cpp Ngram Mod
- Implementation:Infiniflow Ragflow SetMetaDialog Component
Heuristics
- Heuristic:CrewAIInc CrewAI Rate Limiting Strategy
- Heuristic:Marker Inc Korea AutoRAG Hybrid Retrieval Score Normalization
- Heuristic:Snorkel team Snorkel LabelModel Mu Eps Clamping
- Heuristic:Lm sys FastChat Conversation Splitting Token Buffer
- Heuristic:DistrictDataLabs Yellowbrick NaN Data Handling
- Heuristic:Fede1024 Rust rdkafka Multi Version Dependency Hazard
- Heuristic:Promptfoo Promptfoo Cache Configuration Tips
- Heuristic:Datahub project Datahub Validation Across All APIs
- Heuristic:Openai Openai python Warning Deprecated Legacy Response
- Heuristic:Helicone Helicone Anthropic Cache Double Count Prevention
Environments
- Environment:Google research Deduplicate text datasets Rust Cargo Build Environment
- Environment:Testtimescaling Testtimescaling github io GitHub Actions Runner
- Environment:Ggml org Ggml CUDA GPU Environment
- Environment:Truera Trulens Python Core Environment
- Environment:Unslothai Unsloth Llama Cpp
- Environment:Apache Spark Python Environment
- Environment:Turboderp org Exllamav2 Flash Attention Backend
- Environment:InternLM Lmdeploy CUDA GPU Runtime
- Environment:OpenRLHF OpenRLHF vLLM Environment
- Environment:Confident ai Deepeval LLM Provider Credentials