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:Unslothai Unsloth QLoRA SFT Finetuning
- Workflow:BerriAI Litellm Fine Tuning Job
- Workflow:Mlfoundations Open flamingo Few Shot Evaluation
- Workflow:TobikoData Sqlmesh Incremental model development
- Workflow:Openai Openai python Responses API Text Generation
- Workflow:MaterializeInc Materialize Upgrade Testing
- Workflow:Explodinggradients Ragas Test Data Generation
- Workflow:Openclaw Openclaw Gateway Operations And Diagnostics
- Workflow:Langfuse Langfuse Batch export pipeline
- Workflow:Huggingface Peft Prompt Tuning Classification
Principles
- Principle:FlagOpen FlagEmbedding Embedding Similarity Computation
- Principle:Eventual Inc Daft Distributed Scaling Ray
- Principle:Ucbepic Docetl LLM Powered Semantic Filtering
- Principle:DistrictDataLabs Yellowbrick Classifier Visual Evaluation
- Principle:Scikit learn Scikit learn Pipeline Execution
- Principle:Junyanz Pytorch CycleGAN and pix2pix Dataset Acquisition
- Principle:NVIDIA DALI External Data Source
- Principle:Apache Druid SQL Ingestion Monitoring
- Principle:Pola rs Polars Advanced SQL Features
- Principle:NVIDIA DALI Generic Iterator
Implementations
- Implementation:Openai Openai agents python HostedMCP Connector Pattern
- Implementation:Norrrrrrr lyn WAInjectBench text ensemble detect
- Implementation:Ggml org Llama cpp Arg Header
- Implementation:Pola rs Polars SQLContext Constructor
- Implementation:Bentoml BentoML BentoBuildConfig
- Implementation:Haosulab ManiSkill AssetData
- Implementation:Guardrails ai Guardrails Embedding
- Implementation:Microsoft Onnxruntime TrainingSession
- Implementation:MaterializeInc Materialize Blns Test Strings
- Implementation:Deepspeedai DeepSpeed Real Accelerator
Heuristics
- Heuristic:OpenHands OpenHands Streamable HTTP Over SSE
- Heuristic:Promptfoo Promptfoo WAL Mode Network Filesystem
- Heuristic:Mlc ai Web llm Tokenizer JSON Preference
- Heuristic:PacktPublishing LLM Engineers Handbook Dataset Generation Quality Filters
- Heuristic:Marker Inc Korea AutoRAG Passage Filter Safety Minimum
- Heuristic:Openclaw Openclaw Conservative Error Retry Classification
- Heuristic:Mit han lab Llm awq Kernel Selection Thresholds
- Heuristic:Sgl project Sglang Chunked Prefill OOM Prevention
- Heuristic:Diagram of thought Diagram of thought Strict Vs Flexible Critic Rigor
- Heuristic:SqueezeAILab ETS Softmax Temperature Tuning
Environments
- Environment:Junyanz Pytorch CycleGAN and pix2pix Python PyTorch Runtime
- Environment:Elevenlabs Elevenlabs python Python Httpx
- Environment:Kserve Kserve SRIOV RDMA Network
- Environment:Lm sys FastChat GPU CUDA Inference
- Environment:BerriAI Litellm PostgreSQL Database
- Environment:Apache Hudi Flink Runtime Environment
- Environment:ARISE Initiative Robomimic Robosuite Simulation Backend
- Environment:ChenghaoMou Text dedup Suffix Array External Tools
- Environment:Dotnet Machinelearning OneDal Acceleration
- Environment:Lance format Lance Cloud Storage Credentials