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:Sail sg LongSpec Speculative Decoding Inference
- Workflow:Openai Openai node Chat Completion
- Workflow:Togethercomputer Together python Embeddings And Reranking
- Workflow:SeldonIO Seldon core Inference Pipeline
- Workflow:NVIDIA NeMo Curator Fuzzy Deduplication
- Workflow:Isaac sim IsaacGymEnvs Domain Randomization Training
- Workflow:Protectai Llm guard Scanner Benchmarking
- Workflow:Mistralai Client python Function Calling
- Workflow:FMInference FlexLLMGen Text Completion API
- Workflow:Huggingface Datatrove FineWeb Dataset Creation
Principles
- Principle:Ggml org Llama cpp Text Retrieval
- Principle:Microsoft DeepSpeedExamples RLHF Data Preparation
- Principle:Duckdb Duckdb Benchmark Build Configuration
- Principle:SeldonIO Seldon core Experiment Execution
- Principle:Mlc ai Web llm Cross Thread Request Forwarding
- Principle:Huggingface Optimum Calibration Data Preparation
- Principle:Langfuse Langfuse Ingestion Queue Dispatch
- Principle:Facebookresearch Habitat lab Data Recording
- Principle:CARLA simulator Carla Recording Finalization
- Principle:PrefectHQ Prefect Python Package Configuration
Implementations
- Implementation:Vibrantlabsai Ragas PromptMixin
- Implementation:Langgenius Dify Navigation Utils
- Implementation:Turboderp org Exllamav2 Ext QAttn H
- Implementation:Avhz RustQuant Heston93 Model
- Implementation:Facebookresearch Habitat lab ActionSpace
- Implementation:Cohere ai Cohere python AwsChatModels
- Implementation:Apache Airflow Configuration Parser
- Implementation:LMCache LMCache CacheGen Decoder
- Implementation:Ollama Ollama Llama Base64
- Implementation:Marker Inc Korea AutoRAG Generate Simple QA Dataset
Heuristics
- Heuristic:Openai Evals Chat Format Recommendation
- Heuristic:Shiyu coder Kronos Learning Rate And Optimizer Tuning
- Heuristic:DataExpert io Data engineer handbook Watermark Late Arrival Tolerance
- Heuristic:MarketSquare Robotframework browser Windows Shell NPM Workaround
- Heuristic:Axolotl ai cloud Axolotl Gradient Checkpointing Reentrant Rules
- Heuristic:Mlc ai Mlc llm Optimization Level Selection
- Heuristic:PacktPublishing LLM Engineers Handbook LoRA Finetuning Parameters
- Heuristic:Scikit learn contrib Imbalanced learn Sparse Matrix Handling
- Heuristic:Huggingface Transformers Dataloader Pin Memory NonBlocking
- Heuristic:Huggingface Alignment handbook DDP Bias Buffer Ignore
Environments
- Environment:Fede1024 Rust rdkafka CI Test Runner
- Environment:Anthropics Anthropic sdk python Azure Foundry Environment
- Environment:Vespa engine Vespa Java 17 Build Runtime
- Environment:Alibaba MNN ARM Mobile Environment
- Environment:Turboderp org Exllamav2 Flash Attention Backend
- Environment:Vllm project Vllm Intel XPU
- Environment:Marker Inc Korea AutoRAG API Keys Configuration
- Environment:Huggingface Datatrove Processing Dependencies
- Environment:Microsoft Agent framework Python 3 10 Runtime
- Environment:Infiniflow Ragflow GPU CUDA Environment