Distillation and model compression · MLD-1328
Weight-only quantization
Quantizing stored weights while keeping activations or computation at a higher precision.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Serve a language model with low-bit weights.
Original caveat
Actual kernels may still use mixed internal arithmetic.
Context and aliases
Level: Intermediate. Stages: Training · Adaptation · Deployment.
Tags: DL · SLM · LLM.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Distilling the Knowledge in a Neural Network ↗ · Consulted
- PEFT: LoRA conceptual guide ↗ · Consulted
- PEFT: quantization guide ↗ · Consulted
- Original reference URL ↗