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:Pytorch Serve LLM Deployment vLLM
- Workflow:Speechbrain Speechbrain Speaker Embedding Training
- Workflow:Cleanlab Cleanlab Multiannotator Consensus
- Workflow:Arize ai Phoenix Dataset and Experiment Lifecycle
- Workflow:TobikoData Sqlmesh Github CICD automation
- Workflow:Apache Hudi Docker Demo Setup
- Workflow:Vllm project Vllm Offline Text Generation
- Workflow:Microsoft Semantic kernel Kernel Setup And Chat Completion
- Workflow:LMCache LMCache KV Cache Offloading
- Workflow:CrewAIInc CrewAI Crew Training And Testing
Principles
- Principle:FlagOpen FlagEmbedding Cross Encoder Reranking
- Principle:Marker Inc Korea AutoRAG Results Dashboard
- Principle:Avhz RustQuant Business Calendar
- Principle:Iterative Dvc SCM Introspection
- Principle:Googleapis Python genai Content Generation With Cache
- Principle:Eric mitchell Direct preference optimization Dropout Disabling
- Principle:LaurentMazare Tch rs Neural Style Transfer
- Principle:Tensorflow Serving HTTP Server Implementation
- Principle:Langgenius Dify Application Creation
- Principle:Facebookresearch Audiocraft Language Model Export
Implementations
- Implementation:Predibase Lorax Flash SantaCoder Modeling
- Implementation:Langgenius Dify Embed Widget
- Implementation:Axolotl ai cloud Axolotl Load Tokenizer
- Implementation:Datajuicer Data juicer Job Monitor
- Implementation:ThreeSR Awesome Inference Time Scaling Git Commit And Push Function
- Implementation:Langfuse Langfuse IngestionQueue
- Implementation:NVIDIA TransformerEngine Float8Blockwise Storage
- Implementation:Protectai Llm guard Benchmark run
- Implementation:Promptfoo Promptfoo Cache Migration
- Implementation:Open compass VLMEvalKit ImageMCQDataset Build Prompt
Heuristics
- Heuristic:OpenHands OpenHands Streamable HTTP Over SSE
- Heuristic:FMInference FlexLLMGen Weight Compression 4bit
- Heuristic:MaterializeInc Materialize CI Agent Prioritization
- Heuristic:Anthropics Anthropic sdk python Retry Backoff Strategy
- Heuristic:Bitsandbytes foundation Bitsandbytes Outlier Threshold Detection
- Heuristic:Speechbrain Speechbrain Dynamic Mixing Parameters
- Heuristic:TA Lib Ta lib python Thread Safety With Abstract API
- Heuristic:ChenghaoMou Text dedup False Positive Verification Tradeoff
- Heuristic:Microsoft BIPIA OpenAI Rate Limit Retry
- Heuristic:OpenBMB UltraFeedback GPU Memory Utilization
Environments
- Environment:Sgl project Sglang OpenAI
- Environment:Deepspeedai DeepSpeed Python Runtime Environment
- Environment:Lance format Lance Python Environment
- Environment:Microsoft Autogen LLM Provider API Keys
- Environment:Openclaw Openclaw Gateway Network Ports
- Environment:ArroyoSystems Arroyo Python UDF Runtime
- Environment:VainF Torch Pruning CUDA GPU Benchmarking
- Environment:Unstructured IO Unstructured Ingest CLI
- Environment:Duckdb Duckdb Extension Distribution Env
- Environment:Huggingface Datasets PyTorch Integration