Related papers: SwiftKV: Fast Prefill-Optimized Inference with Kno…
Edge acceleration for large language models is crucial for their widespread application; however, achieving fast attention inference and efficient decoding on resource-constrained edge accelerators remains challenging. This paper presents…
With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for efficient support of high-throughput inference. However, as the key-value (KV) cache expands with the sequence length, the…
Generating long sequences of tokens given a long-context input is a very compute-intensive inference scenario for large language models (LLMs). One prominent inference speed-up approach is to construct a smaller key-value (KV) cache,…
While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computational efficiency and memory usage in both prefill and…
Large language models face significant computational and memory challenges when processing long contexts. During inference, efficient management of the key-value (KV) cache, which stores intermediate activations for autoregressive…
Disaggregated inference has become an essential framework that separates the prefill (P) and decode (D) stages in large language model inference to improve throughput. However, the KV cache transfer faces significant delays between prefill…
Large language models (LLMs) are widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant deployment challenges, primarily due to the KV cache whose size…
Efficient inference for on-device Large Language Models (LLMs) remains challenging due to limited hardware resources and the high cost of the prefill stage, which processes the full input context to construct Key-Value (KV) caches. We…
Large reasoning models (LRMs) often incur significant key-value (KV) cache overhead, due to their linear growth with the verbose chain-of-thought (CoT) reasoning. This incurs both memory overhead and throughput bottlenecks, limiting…
As large language models (LLMs) tackle increasingly complex tasks and longer documents, their computational and memory costs during inference become a major bottleneck. To address this, we propose PromptDistill, a novel, training-free…
Recently, large vision-language models (LVLMs) have rapidly gained popularity for their strong generation and reasoning capabilities given diverse multimodal inputs. However, these models incur significant computational and memory overhead…
Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency in Large Language Models (LLMs), its direct adoption in LVLMs introduces substantial…
Large Language Models (LLMs) have made remarkable progress in processing extensive contexts, with the Key-Value (KV) cache playing a vital role in enhancing their performance. However, the growth of the KV cache in response to increasing…
As Large Language Models (LLMs) scale to support context windows exceeding one million tokens, the linear growth of Key-Value (KV) cache imposes severe memory capacity and bandwidth bottlenecks, constraining the efficiency of long-context…
Efficient inference of large language models (LLMs) is hindered by an ever-growing key-value (KV) cache, making KV cache compression a critical research direction. Traditional methods selectively evict less important KV cache entries, which…
Efficient long-context inference in Large Language Models (LLMs) is severely constrained by the Key-Value (KV) cache memory wall, yet existing pruning methods force a choice between low-latency heuristics that sacrifice precision and…
We observe two major trends in LLM-based generative AI: (1) inference is becoming the dominant factor in terms of cost and power consumption, surpassing training, and (2) retrieval augmented generation (RAG) is becoming prevalent. When…
KV cache eviction has emerged as an effective solution to alleviate resource constraints faced by LLMs in long-context scenarios. However, existing token-level eviction methods often overlook two critical aspects: (1) their irreversible…
Large Language Models (LLMs) require significant GPU memory when processing long texts, with the key value (KV) cache consuming up to 70\% of total memory during inference. Although existing compression methods reduce memory by evaluating…
The increasing memory demand of the Key-Value (KV) cache poses a significant bottleneck for Large Language Models (LLMs) in long-context applications. Existing low-rank KV compression methods reduce this footprint by modifying model…