KV-cache Grafting: Freezing Small Models Makes Them Stronger
Corbenci · hf · 2026-07-17
Making Frozen Small Models Cheaper and Stronger with KV-cache Grafting
This work proposes a method to boost small model capabilities and reduce inference costs without changing weights: storing verified knowledge as byte-exact KV states, which are later grafted back into new inference contexts.
Core Features
- Recovery is bit-level identical: Under fixed deterministic configurations, the logits after grafting are byte-for-byte identical to recomputed results
- The paper verified byte-exactness on 12B and 31B model scales across two GPU targets
- Provided committed input/output hashes for easy verification
Results
- On AIME 2025, frozen Gemma-4-12B improved from 80.0% to 93.3%
- On recurring cases, 8 problems originally unsolvable within a 401,026 token budget were solved using cached verified answers within 61 decode tokens
- The paper claims this equates to 6,574x fewer tokens and roughly 8,700x lower energy consumption
- Usable context length expanded from 32,768 to 2,854,766 tokens without increasing extra accelerator memory
The authors describe this as a "verified-knowledge flywheel": knowledge is verified once and reused multiple times.
Related event: KV-Cache Grafting Boosts Frozen Small Models(2 posts)→
More from Infra
- AWS tutorial: fleet-wide edge CV model lifecycle with SageMaker SDK v3, ~$0.07 per run — AWS ML Blog · 2026-10-27
- Qwen3.8-27B hits 40 tok/s on Jetson Thor with INT4 + MTP, accuracy beats FP16 — No-Dragonfly6246 · 2026-10-27
- Celesto launches CI runners nearly 90% cheaper than GitHub Actions, with agent sandboxes — aniketmaurya · 2026-10-27
- Supabase founders on rebuilding the backend for a billion AI-built apps — Latent Space · 2026-10-27
- AW-0 runs at 230ms on a single RTX 5090, 2.4x faster than autoregressive code planning — trevordarrell · 2026-10-27
- Site tracks US city council topics: data centers rank only behind pickleball courts — zakkohane · 2026-10-27