DuoAttention identifies retrieval heads requiring full KV cache and streaming heads using constant-length cache to reduce memory and latency in long-context LLM inference.
H _2 o: Heavy-hitter oracle for efficient generative inference of large language models, 2023 b
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2representative citing papers
StreamingLLM lets finite-window LLMs generalize to infinite-length sequences by retaining initial-token KV states as attention sinks, enabling stable streaming inference up to 4M tokens.
citing papers explorer
-
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
DuoAttention identifies retrieval heads requiring full KV cache and streaming heads using constant-length cache to reduce memory and latency in long-context LLM inference.
-
Efficient Streaming Language Models with Attention Sinks
StreamingLLM lets finite-window LLMs generalize to infinite-length sequences by retaining initial-token KV states as attention sinks, enabling stable streaming inference up to 4M tokens.