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:Run llama Llama index Data Ingestion Pipeline
- Workflow:Turboderp org Exllamav2 LoRA Adapter Inference
- Workflow:NVIDIA NeMo Curator Video Curation Pipeline
- Workflow:Ggml org Llama cpp Model Quantization
- Workflow:Arize ai Phoenix Trace Ingestion Pipeline
- Workflow:Facebookresearch Habitat lab HITL Interactive Evaluation
- Workflow:EvolvingLMMs Lab Lmms eval Server Mode Evaluation
- Workflow:Ggml org Llama cpp Speculative Decoding
- Workflow:Huggingface Trl Direct Preference Optimization
- Workflow:Turboderp org Exllamav2 Bulk Dataset Inference
Principles
- Principle:Microsoft DeepSpeedExamples Instruction Dataset Preparation
- Principle:Rapidsai Cuml Time Series Forecasting
- Principle:NVIDIA NeMo Curator Video Embedding
- Principle:Shiyu coder Kronos Single Series Forecasting
- Principle:Ggml org Llama cpp GGUFFormat
- Principle:Triton inference server Server Performance Verification
- Principle:Bitsandbytes foundation Bitsandbytes 4bit Dequantization And Matmul
- Principle:Langgenius Dify Node Level Testing
- Principle:CARLA simulator Carla Walker AI Control
- Principle:Datajuicer Data juicer LLM Content Generation
Implementations
- Implementation:Datajuicer Data juicer VideoResizeAspectRatioMapper
- Implementation:OpenHands OpenHands Tooltip
- Implementation:Avhz RustQuant Lookback Backend
- Implementation:Google deepmind Dm control Obs Buffer
- Implementation:Openai Openai python Response Prompt
- Implementation:Infiniflow Ragflow Agent Hooks
- Implementation:Openai Openai node Conversations Resource
- Implementation:Confident ai Deepeval StepEfficiencyMetric
- Implementation:Infiniflow Ragflow Health Check System
- Implementation:Mit han lab Llm awq Model Worker
Heuristics
- Heuristic:Openai Evals Model Graded Eval Design
- Heuristic:AUTOMATIC1111 Stable diffusion webui GTX 16 Series FP16 Workaround
- Heuristic:FMInference FlexLLMGen Offloading Percent Tuning
- Heuristic:Arize ai Phoenix Warning Deprecated HallucinationEvaluator
- Heuristic:Microsoft Agent framework PowerFx Python Version Limit
- Heuristic:Risingwavelabs Risingwave Memory Cache Eviction Policy
- Heuristic:Alibaba ROLL Reward Clipping Normalization
- Heuristic:Vibrantlabsai Ragas Reasoning Model Parameter Constraints
- Heuristic:Apache Druid Query Error Suggestion Patterns
- Heuristic:Mlfoundations Open flamingo RICES Feature Caching
Environments
- Environment:OpenHands OpenHands Integration Credentials
- Environment:LLMBook zh LLMBook zh github io Bitsandbytes Quantization Environment
- Environment:Ggml org Llama cpp CUDA GPU Environment
- Environment:Trailofbits Fickling PyTorch
- Environment:Marker Inc Korea AutoRAG VLLM Environment
- Environment:Intel Ipex llm XPU Serving Environment
- Environment:PacktPublishing LLM Engineers Handbook Selenium Chrome Crawler Environment
- Environment:Run llama Llama index Fsspec Remote Storage
- Environment:Openclaw Openclaw Gateway Network Ports
- Environment:Elevenlabs Elevenlabs python PyAudio