Related papers: QuantSpec: Self-Speculative Decoding with Hierarch…
Large Language Models (LLMs) have demonstrated remarkable proficiency across a wide range of tasks. However, LLMs often require larger batch sizes to enhance throughput or longer context lengths to meet task demands, which significantly…
Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI. Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value (KV) cache during…
Speculative decoding speeds up autoregressive generation in Large Language Models (LLMs) through a two-step procedure, where a lightweight draft model proposes tokens which the target model then verifies in a single forward pass. Although…
As the demand for long-context large language models (LLMs) increases, models with context windows of up to 128K or 1M tokens are becoming increasingly prevalent. However, long-context LLM inference is challenging since the inference speed…
Growing demands from tasks like code generation, deep reasoning, and long-document understanding have made long-context generation a crucial capability for large language models (LLMs). Speculative decoding is one of the most direct and…
Vision-language models (VLMs) have demonstrated strong capabilities in multimodal perception and reasoning. However, deploying large VLMs on mobile devices remains challenging due to their substantial computational and memory demands. A…
Large Language Models (LLMs) have achieved remarkable progress across reasoning, generation, and decision-making tasks, yet deploying them on mobile, embedded, and edge devices remains particularly challenging. On-device LLM inference is…
Withtherapid advancement of large language models (LLMs), the context length for inference has been continuously increasing, leading to an exponential growth in the demand for Key-Value (KV) caching. This has resulted in a significant…
Long-context reasoning is a critical capability of large language models (LLMs), enabling applications such as long-document understanding, summarization, and code generation. However, efficient autoregressive inference relies on the…
Disaggregated Large Language Model (LLM) inference has gained popularity as it separates the computation-intensive prefill stage from the memory-intensive decode stage, avoiding the prefill-decode interference and improving resource…
Vision-language models (VLMs) achieve strong performance on multimodal tasks but suffer from high inference latency due to large model sizes and long multimodal contexts. Speculative decoding has recently emerged as an effective…
Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the…
Recently the generative Large Language Model (LLM) has achieved remarkable success in numerous applications. Notably its inference generates output tokens one-by-one, leading to many redundant computations. The widely-used KV-Cache…
The deployment of long-context Large Language Models (LLMs) poses significant challenges due to the intense computational cost of self-attention and the substantial memory overhead of the Key-Value Cache (KV Cache). In this paper, we…
Large language models (LLMs) rely on key-value cache (KV cache) to accelerate decoding by reducing redundant computations. However, the KV cache memory usage grows substantially with longer text sequences, posing challenges for efficient…
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,…
Large language models achieve impressive performance across diverse tasks but exhibit high inference latency due to their large parameter sizes. While quantization reduces model size, it often leads to performance degradation compared to…
Speculative decoding is an effective and lossless method for Large Language Model (LLM) inference acceleration. It employs a smaller model to generate a draft token sequence, which is then verified by the original base model. In multi-GPU…
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…
The key-value (KV) cache in large language models presents a significant memory bottleneck during inference, growing linearly with sequence length and often exceeding the memory footprint of model weights themselves. We implement and…