Distillation and model compression · MLD-0611
KV-cache quantization
Reducing the precision of cached attention keys and values.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Lower long-context serving memory.
Original caveat
Errors can accumulate differently from weight quantization.
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 ↗