conftrace_

kv cache quantization

10 papers

Explore in graph

Also known as

KV

Co-occurring keywords

model compression (3302) large language model (13587) memory efficiency (261) kv cache (74) inference optimization (219) memory optimization (114) 1-bit quantization (9) inference efficiency (248) language model (4599) rotary position embedding (32)

Papers

MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning ACL 2026
Efficient Multimodal Large Language Model via Dynamic KV Cache Quantization AAAI 2026
Accurate KV Cache Quantization with Outlier Tokens Tracing ACL 2025
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead AAAI 2025
MiniKV: Pushing the Limits of 2-Bit KV Cache via Compression and System Co-Design for Efficient Long Context Inference ACL 2025
XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression EMNLP 2025
AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations COLING 2025
RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations IJCAI 2025
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization NIPS 2024
ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification NIPS 2024