17. AI and Language Models
CPU LLM inference over GGUF models: loading, tokenization, generation, and chat.
- 17.1. dasLLAMA LLM inference: models, sessions, generation, chat
- 17.1.1. Type aliases
- 17.1.2. Types
- 17.1.3. Model loading and sessions
- 17.1.4. Prefix cache
- 17.1.5. Tokenizer
- 17.1.6. Evaluation and sampling
- 17.1.7. Generation
- 17.1.8. Embeddings
- 17.1.9. Vision and audio encoders
- 17.1.10. Chat
- 17.1.11. Tool calling
- 17.1.12. Reasoning (thinking models)
- 17.1.13. Operations: prepared images and dispatch
- 17.1.14. Operations: GPU tier and model slots