🧠
LLM
Roadmap
☰
Overview
Mindmap
Roadmap
Resources
Skills
Projects
Toolbox
Progress
🌙
Essential Toolbox
The tools and frameworks you'll use throughout your journey
🧮 Frameworks & Libraries
PyTorch
Core
Hugging Face Transformers
Core
JAX
/
Flax
Research
DeepSpeed
/
Megatron-LM
Training
PEFT (LoRA, QLoRA)
Fine-tuning
TRL (Transformer RL)
RLHF
Unsloth
Fast Fine-tune
🚀 Inference & Serving
vLLM
Serving
TensorRT-LLM
NVIDIA
llama.cpp
/
Ollama
Local
Text Generation Inference
HF
SGLang
Fast
Triton Inference Server
Production
🗄️ Data & Vector DBs
ChromaDB
Simple
Pinecone
Managed
Weaviate
Open Source
Milvus
Scalable
Qdrant
Fast
FAISS
Meta
🔗 App Frameworks
LangChain
/
LangGraph
Agents
LlamaIndex
RAG
DSPy
Programmatic
Semantic Kernel
Microsoft
CrewAI
Multi-Agent
Gradio
/
Streamlit
UI
📊 Evaluation & Monitoring
lm-evaluation-harness
Benchmarks
Weights & Biases
Tracking
FastChat / MT-Bench
Chat Eval
DeepEval
LLM Testing
MLflow
ML Ops
Argilla
Data Curation
📐 Data & Tokenization
HF Tokenizers
Fast
SentencePiece
Google
tiktoken
OpenAI
HF Datasets
Data Loading
RedPajama
Pre-train Data
minbpe
Learn BPE