STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
[Przetwarzanie języka] Autorzy: Bingchen Yao, Haobo Xu, Haokun Lin i 6 więcej
Linear attention replaces growing KV caches with fixed-size recurrent states, yet these persistent states can become a substantial memory bottleneck under concurrent serving. Directly quantizing recurrent states to low precision often leads to severe accuracy degradation, as quantization errors propagate through successive state updates. We discover that the impact of these errors depends on two complementary dimensions: temporally, errors in long-lived memory can persist across many decoding steps; spatially, errors in different key rows affect model outputs differently, while state magnitudes vary substantially along both rows and columns. Motivated by these observations, we propose STEPQuant, a spatial-temporal post-training quantization framework for Delta-rule recurrent states. STEPQuant allocates precision according to error magnitude and memory lifetime, and jointly fits key-row …
- Kategoria arxiv
- cs.CL
- Kategoria
- Przetwarzanie języka