kv-cache-compression topic

This is the official repo of "QuickLLaMA: Query-aware Inference Acceleration for Large Language Models"

dvlab-research

Pytorch implementation for "Compressed Context Memory For Online Language Model Interaction" (ICLR'24)

snu-mllab

xKV: Cross-Layer SVD for KV-Cache Compression

abdelfattah-lab

Unified KV Cache Compression Methods for Auto-Regressive Models

Zefan-Cai

LLM KV cache compression made easy

NVIDIA

Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.

Zefan-Cai

[NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)

snu-mllab

Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)

itsnamgyu

[ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection

shadowpa0327

(ACL 2025 oral) SCOPE: Optimizing KV Cache Compression in Long-context Generation

Linking-ai