A tiered KV cache architecture computes per-head per-step error bounds on quantized attention and uses adaptive fallback to guarantee bounded or exact outputs relative to FP16 reference.
RULER: What’s the real context size of your long- context language models?COLM, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Runtime-Certified Bounded-Error Quantized Attention
A tiered KV cache architecture computes per-head per-step error bounds on quantized attention and uses adaptive fallback to guarantee bounded or exact outputs relative to FP16 reference.