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:Pyro ppl Pyro Bayesian Regression
- Workflow:Langchain ai Langchain Adding Partner Integration
- Workflow:Lucidrains X transformers Encoder Decoder Sequence to Sequence
- Workflow:Mbzuai oryx Awesome LLM Post training Awesome List Curation
- Workflow:CarperAI Trlx RLHF Dialogue Alignment
- Workflow:Microsoft Autogen Tool Augmented Agent
- Workflow:Roboflow Rf detr Custom Dataset Finetuning
- Workflow:Scikit learn Scikit learn Data Preprocessing Pipeline
- Workflow:MarketSquare Robotframework browser JavaScript Extension
- Workflow:Iterative Dvc Remote Data Sync
Principles
- Principle:Bigscience workshop Petals Autoregressive Generation
- Principle:Huggingface Trl GRPO Model Saving
- Principle:Pytorch Serve LLM Text Generation
- Principle:Zai org CogVideo Caption Generation
- Principle:Pytorch Serve IPEX Quantized Inference
- Principle:Ggml org Llama cpp SpeculativeDecoding
- Principle:Apache Kafka Topic Listing
- Principle:Ollama Ollama ModelArchitecture
- Principle:Romsto Speculative Decoding Ngram Assisted Speculative Decoding
- Principle:Sktime Pytorch forecasting Learning Rate Finding
Implementations
- Implementation:Nautechsystems Nautilus trader BacktestEngine Add Venue
- Implementation:Online ml River Imblearn RandomSampler
- Implementation:Apache Druid QueryParametersDialog
- Implementation:OpenHands OpenHands Business Router Pattern
- Implementation:NVIDIA TransformerEngine Core Tensor Impl
- Implementation:Ollama Ollama Llama Server
- Implementation:InternLM Lmdeploy Request
- Implementation:Treeverse LakeFS Java SDK Model AccessKeyCredentials
- Implementation:Huggingface Transformers AutoModelForCausalLM From Pretrained For PEFT
- Implementation:Haosulab ManiSkill AllegroHand
Heuristics
- Heuristic:Deepset ai Haystack Document Splitting Defaults
- Heuristic:Avhz RustQuant Learning Rate Tuning
- Heuristic:Microsoft Onnxruntime Graph Optimization Level Selection
- Heuristic:Tencent Ncnn FP16 Precision Selection
- Heuristic:ClickHouse ClickHouse Jemalloc Production Requirement
- Heuristic:InternLM Lmdeploy KV Quantization Tradeoffs
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Image Size Multiple of Four
- Heuristic:Turboderp org Exllamav2 Dynamic Generator Tuning
- Heuristic:BerriAI Litellm Cooldown Threshold Tuning
- Heuristic:Hiyouga LLaMA Factory CUDA Memory Optimization
Environments
- Environment:Unstructured IO Unstructured Ingest CLI
- Environment:Vllm project Vllm NVIDIA CUDA
- Environment:Sgl project Sglang Python Dependencies
- Environment:CARLA simulator Carla Simulation Runtime
- Environment:Apache Druid Druid Operator Kubernetes
- Environment:Vibrantlabsai Ragas Optional NLP Metrics Environment
- Environment:Unslothai Unsloth CUDA VLLM
- Environment:Haifengl Smile Quarkus Serve Environment
- Environment:Lm sys FastChat LoRA QLoRA Training Environment
- Environment:Bigscience workshop Petals Python Hivemind