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:CrewAIInc CrewAI Crew Training And Testing
- Workflow:CarperAI Trlx RLHF Summarization Pipeline
- Workflow:TobikoData Sqlmesh Model development and testing
- Workflow:Explodinggradients Ragas Test Data Generation
- Workflow:Confident ai Deepeval AI Agent Evaluation
- Workflow:DevExpress Testcafe Basic Test Authoring
- Workflow:Dagster io Dagster ML Pipeline
- Workflow:PacktPublishing LLM Engineers Handbook LLM Finetuning
- Workflow:Mlflow Mlflow Prompt Management
- Workflow:Unstructured IO Unstructured Performance Profiling
Principles
- Principle:Deepspeedai DeepSpeed Engine Initialization
- Principle:Ggml org Llama cpp Parallel Request Handling
- Principle:AUTOMATIC1111 Stable diffusion webui Merge output options
- Principle:LaurentMazare Tch rs Custom Optimizer Integration
- Principle:Wandb Weave Distribution Build
- Principle:Cohere ai Cohere python Server Sent Events Decoding
- Principle:Ray project Ray Remote Function Definition
- Principle:AUTOMATIC1111 Stable diffusion webui Webui Disk Caching
- Principle:Kserve Kserve Controller Deployment
- Principle:Hiyouga LLaMA Factory Direct Preference Optimization
Implementations
- Implementation:Huggingface Peft CPTConfig
- Implementation:Pytorch Serve Llama2 Generate
- Implementation:Turboderp org Exllamav2 Tokenize Calibration
- Implementation:Run llama Llama index RecursiveRetriever
- Implementation:CrewAIInc CrewAI Manager Agent Setup
- Implementation:Avhz RustQuant Cashflow
- Implementation:Speechbrain Speechbrain Prepare Librimix
- Implementation:FlowiseAI Flowise SignIn
- Implementation:Intel Ipex llm AutoModelForCausalLM From Pretrained bf16
- Implementation:Vllm project Vllm CPU Types ARM
Heuristics
- Heuristic:FlagOpen FlagEmbedding Warning Deprecated Search Demo
- Heuristic:Langgenius Dify Warning Deprecated Default Datasource Auth
- Heuristic:Huggingface Peft Gradient Checkpointing With Quantization
- Heuristic:NVIDIA NeMo Aligner Higher Stability Log Probs
- Heuristic:Apache Paimon Compression Tuning
- Heuristic:Huggingface Peft LoRA Initialization Strategy Selection
- Heuristic:Vibrantlabsai Ragas Warning Deprecated Legacy LLM Wrappers
- Heuristic:Bentoml BentoML Adaptive Batching Tuning
- Heuristic:Risingwavelabs Risingwave LSM Compaction Tuning
- Heuristic:Datahub project Datahub Venv Copies Mode
Environments
- Environment:Run llama Llama index Sentence Transformers Finetuning
- Environment:HKUDS AI Trader Python LangChain Runtime
- Environment:Google deepmind Dm control Python MuJoCo Runtime
- Environment:Getgauge Taiko Node Runtime
- Environment:Groq Groq python Python Groq SDK
- Environment:Farama Foundation Gymnasium JAX Functional Backend
- Environment:Princeton nlp SimPO VLLM Inference
- Environment:Google research Deduplicate text datasets Python HuggingFace Environment
- Environment:Pola rs Polars Rust Build Environment
- Environment:Huggingface Alignment handbook BitsAndBytes CUDA