Skip to content
conftrace_

memory requirement

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

low-bit representation (1) large language model (1) accuracy deviation (1) clustered head attention (1) k,v cache (1) quantization-aware training (1) self attention (1) inference latency (1) low-bit quantization (1) parameter efficient (1)

Papers

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models ACL 2025 CHAI: Clustered Head Attention for Efficient LLM Inference ICML 2024