Related papers: You Need an Encoder for Native Position-Independen…
Key-Value (KV) cache has become a bottleneck of LLMs for long-context generation. Despite the numerous efforts in this area, the optimization for the decoding phase is generally ignored. However, we believe such optimization is crucial,…
Recent large language model applications, such as Retrieval-Augmented Generation and chatbots, have led to an increased need to process longer input contexts. However, this requirement is hampered by inherent limitations. Architecturally,…
Using special tokens (e.g., gist, memory, or compressed tokens) to compress context information is a common practice for large language models (LLMs). However, existing approaches often neglect that position encodings inherently induce…
Large Language Model (LLM) inference uses an autoregressive manner to generate one token at a time, which exhibits notably lower operational intensity compared to earlier Machine Learning (ML) models such as encoder-only transformers and…
We present Cacheback Decoding, a training-free and model-agnostic speculative decoding method that exploits the locality in language to accelerate Large Language Model (LLM) inference. Cacheback leverages only Least Recently Used (LRU)…
The revolutionary capabilities of Large Language Models (LLMs) are attracting rapidly growing popularity and leading to soaring user requests to inference serving systems. Caching techniques, which leverage data reuse to reduce computation,…
While convolution and self-attention are extensively used in learned image compression (LIC) for transform coding, this paper proposes an alternative called Contextual Clustering based LIC (CLIC) which primarily relies on clustering…
Optimizing inference for long-context large language models (LLMs) is increasingly important due to the quadratic compute and linear memory cost of Transformers. Existing approximate inference methods, including key-value (KV) cache…
Key-Value (KV) caching is a common technique to enhance the computational efficiency of Large Language Models (LLMs), but its memory overhead grows rapidly with input length. Prior work has shown that not all tokens are equally important…
Answering real-world tourism questions that seek Point-of-Interest (POI) recommendations is challenging, as it requires both spatial and non-spatial reasoning, over a large candidate pool. The traditional method of encoding each pair of…
Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks, yet often suffer from inefficiencies due to redundant visual tokens. Existing token merging methods reduce sequence length but frequently…
Incorporating external knowledge in large language models (LLMs) enhances their utility across diverse applications, but existing methods have trade-offs. Retrieval-Augmented Generation (RAG) fetches evidence via similarity search, but key…
The Key-Value (KV) cache is central to the efficiency of transformer-based large language models (LLMs), storing previously computed vectors to accelerate inference. Yet, as sequence length and batch size grow, the cache becomes a major…
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…
Since local LLM inference on resource-constrained edge devices imposes a severe performance bottleneck, this paper proposes distributed prompt caching to enhance inference performance by cooperatively sharing intermediate processing states…
Large Language Models (LLMs) confront significant memory challenges due to the escalating KV cache with increasing sequence length. As a crucial technique, existing cross-layer KV cache sharing methods either necessitate modified model…
Large Language Models (LLMs), epitomized by ChatGPT's release in late 2022, have revolutionized various industries with their advanced language comprehension. However, their efficiency is challenged by the Transformer architecture's…
The KV cache used in large language models has linearly growing time complexity, so LLMs face memory blow-up and reduced decoding efficiency when they process long contexts. Current KV Cache eviction has become an important research…
During inference for transformer-based large language models (LLM), prefilling is the computation of the key-value (KV) cache for input tokens in the prompt prior to autoregressive generation. For longer input prompt lengths, prefilling…
The rapid growth of high-resolution scientific simulations and observation systems is generating massive spatiotemporal datasets, making efficient, error-bounded compression increasingly important. Meanwhile, decoder-only large language…