KVCodec uses GPU-native video codecs and pipelined fetching to compress and transmit KV caches, delivering up to 3.51x faster TTFT than prior methods while preserving accuracy.
Instinfer: In-storage attention offloading for cost-effective long-context llm inference
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
DUAL-BLADE uses a dual-path KV-cache framework with NVMe-direct access to reduce prefill and decode latency by up to 33% and 42% while improving SSD utilization 2.2x under tight memory budgets.
MCAP uses load-time Monte Carlo profiling to estimate layer importance, enabling dynamic quantization (W4A8 vs W4A16) and memory tiering (GPU/RAM/SSD) that delivers 1.5-1.8x higher decode throughput than llama-cpp Q4_0 on NVIDIA T4 while fitting models into previously infeasible memory budgets.
SinkRouter identifies attention sinks as training-derived fixed points and routes around them to skip redundant KV-cache loads, delivering up to 2.03x decoding speedup on long-context benchmarks.
citing papers explorer
-
Efficient Remote KV Cache Reuse with GPU-native Video Codec
KVCodec uses GPU-native video codecs and pipelined fetching to compress and transmit KV caches, delivering up to 3.51x faster TTFT than prior methods while preserving accuracy.
-
DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference
DUAL-BLADE uses a dual-path KV-cache framework with NVMe-direct access to reduce prefill and decode latency by up to 33% and 42% while improving SSD utilization 2.2x under tight memory budgets.
-
MCAP: Deployment-Time Layer Profiling for Memory-Constrained LLM Inference
MCAP uses load-time Monte Carlo profiling to estimate layer importance, enabling dynamic quantization (W4A8 vs W4A16) and memory tiering (GPU/RAM/SSD) that delivers 1.5-1.8x higher decode throughput than llama-cpp Q4_0 on NVIDIA T4 while fitting models into previously infeasible memory budgets.
-
SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models
SinkRouter identifies attention sinks as training-derived fixed points and routes around them to skip redundant KV-cache loads, delivering up to 2.03x decoding speedup on long-context benchmarks.