Distillation and model compression · MLD-0687
Low-bit inference
Running model inference with reduced-precision representations or arithmetic.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Deploy a quantized model on a memory-limited device.
Original caveat
Bit width alone is insufficient to predict quality or latency.
Context and aliases
Level: Intermediate. Stages: Training · Adaptation · Deployment.
Tags: DL · SLM · LLM.
Aliases: None recorded.
Related concepts
Original references
- Distilling the Knowledge in a Neural Network ↗ · Consulted
- PEFT: LoRA conceptual guide ↗ · Consulted
- PEFT: quantization guide ↗ · Consulted
- Original reference URL ↗