the.ai

Inference / Memory

verified

Quantized KV Cache

Store the attention cache in fewer bits. At long context the cache outgrows the weights, so this is where the memory actually is — and unlike the weights, it grows with every request rather than being paid once.

Viz primitive · budget-splitcache-bytes = 8

cache-bytes holds 17% of the budget; rest holds the remaining 83%.

Memory held by the attention cache, against the memory held by the weights, in equal units. Drag the cache up — it is context length that moves it in practice — to watch it overtake the weights; past that crossing it is the only term worth quantising.

8

Reviewed by opendroid · 2026-08-18

  • arXiv:2401.18079 — KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
  • arXiv:2309.06180 — Efficient Memory Management for Large Language Model Serving with PagedAttention