DynamicPTQ uses new metrics of residual-stream dynamics to apply 8-bit activation precision only to quantization-sensitive layers in W4A4KV4 LLM inference, improving perplexity and QA performance over static smoothing baselines.
A review on edge large language models: Design, execution, and applications
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Drop-by-Drop uses additive codebooks and Matryoshka-style training to produce one LLM model whose ordered codebook subsets give accurate reconstructions at successively higher bitwidths under a weighted MSE distortion.
citing papers explorer
-
DynamicPTQ: Mitigating Activation Quantization Collapse via Residual-Stream Dynamics
DynamicPTQ uses new metrics of residual-stream dynamics to apply 8-bit activation precision only to quantization-sensitive layers in W4A4KV4 LLM inference, improving perplexity and QA performance over static smoothing baselines.
-
Multi-Bitwidth Quantization for LLMs Using Additive Codebooks
Drop-by-Drop uses additive codebooks and Matryoshka-style training to produce one LLM model whose ordered codebook subsets give accurate reconstructions at successively higher bitwidths under a weighted MSE distortion.