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:Huggingface Open r1 GRPO Reasoning Training
- Workflow:Apache Druid Batch Data Ingestion
- Workflow:Heibaiying BigData Notes Flink Kafka Streaming Pipeline
- Workflow:MaterializeInc Materialize Docker Image Build
- Workflow:Microsoft Playwright End to end test authoring
- Workflow:Ggml org Ggml Backend Accelerated Computation
- Workflow:Cohere ai Cohere python Tool Use Agentic Chat
- Workflow:Sgl project Sglang Offline Batch Inference
- Workflow:Huggingface Datasets Format Conversion
- Workflow:Protectai Modelscan Programmatic Model Scanning
Principles
- Principle:Deepset ai Haystack Retrieval Recall Evaluation
- Principle:AUTOMATIC1111 Stable diffusion webui Transformer Diffusion Architecture
- Principle:Duckdb Duckdb Zlib Deflate Compression
- Principle:Langchain ai Langchain Chat Model Initialization
- Principle:Bitsandbytes foundation Bitsandbytes FSDP 4bit Quantization
- Principle:Huggingface Trl SFT Trainer Initialization
- Principle:FlagOpen FlagEmbedding Retrieval Augmented Evaluation
- Principle:Eventual Inc Daft Type Casting
- Principle:Anthropics Anthropic sdk python Client Initialization
- Principle:Langfuse Langfuse Experiment Results Aggregation
Implementations
- Implementation:Apache Druid RetentionDialog
- Implementation:AUTOMATIC1111 Stable diffusion webui UI Core JavaScript
- Implementation:Google deepmind Mujoco Platform Interaction
- Implementation:ThreeSR Awesome Inference Time Scaling GitHub PR Review And Merge
- Implementation:Huggingface Datatrove RegexFilter
- Implementation:Haosulab ManiSkill PPO Agent Network
- Implementation:Alibaba MNN Protobuf Generated Table Driven Lite H
- Implementation:Hiyouga LLaMA Factory RM Workflow
- Implementation:Facebookresearch Habitat lab MobileManipulator
- Implementation:Huggingface Datasets DatasetBuilder As Dataset
Heuristics
- Heuristic:Volcengine Verl FSDP Mixed Precision Init
- Heuristic:Dotnet Machinelearning LDA Thread Reservation
- Heuristic:Microsoft Playwright Browser Specific Workarounds
- Heuristic:Neuml Txtai MacOS OpenMP Workaround
- Heuristic:OWASP Www project top 10 for large language model applications Deliberately Insecure Code Isolation
- Heuristic:Haifengl Smile BFGS Convergence Tuning
- Heuristic:Apache Airflow Task Idempotency Pattern
- Heuristic:Allenai Open instruct GPU Memory Utilization
- Heuristic:Haotian liu LLaVA Image Aspect Ratio Padding Strategy
- Heuristic:Treeverse LakeFS Action Cache Wait Tip
Environments
- Environment:Speechbrain Speechbrain HuggingFace Transformers
- Environment:Openclaw Openclaw Gateway Network Ports
- Environment:Guardrails ai Guardrails Python 3 10 Runtime
- Environment:Bentoml BentoML Triton Inference Server
- Environment:Ray project Ray Java Build Environment
- Environment:Kornia Kornia CUDA GPU Environment
- Environment:OpenRLHF OpenRLHF Ray Distributed Environment
- Environment:Liu00222 Open Prompt Injection CUDA Environment
- Environment:Mlfoundations Open flamingo HuggingFace Open CLIP Dependencies
- Environment:ThreeSR Awesome Inference Time Scaling Semantic Scholar API Environment