相关论文: MOM: Memory-Efficient Offloaded Mini-Sequence Infe…

Efficient attentions have greatly improved the computational efficiency of Transformers. However, most existing linear attention mechanisms suffer from an \emph{efficiency degradation} problem, leading to inefficiencies in causal language…

Training with larger mini-batches improves the convergence rate and can yield superior performance. However, training with large mini-batches becomes prohibitive for Large Language Models (LLMs), due to the large GPU memory requirement. To…

Online LLM inference powers many exciting applications such as intelligent chatbots and autonomous agents. Modern LLM inference engines widely rely on request batching to improve inference throughput, aiming to make it cost-efficient when…

In recent years, Mixture-of-Experts (MoE) has emerged as an effective approach for enhancing the capacity of deep neural network (DNN) with sub-linear computational costs. However, storing all experts on GPUs incurs significant memory…

Trained on massive cross-species DNA corpora, DNA large language models (LLMs) learn the fundamental "grammar" and evolutionary patterns of genomic sequences. This makes them powerful priors for DNA sequence modeling, particularly over long…

Large Vision-Language Models (VLMs) deliver exceptional performance but require significant computational resources, limiting their deployment on mobile and edge devices. Smaller VLMs typically mirror design choices of larger models, such…

The quadratic complexity and indefinitely growing key-value (KV) cache of standard Transformers pose a major barrier to long-context processing. To overcome this, we introduce the Collaborative Memory Transformer (CoMeT), a novel…

Efficient deployment of large language models, particularly Mixture of Experts (MoE), on resource-constrained platforms presents significant challenges, especially in terms of computational efficiency and memory utilization. The MoE…

Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding…

Modern large language model (LLM) applications increasingly rely on long conditioning prefixes to control model behavior at inference time. While prefix-augmented inference is effective, it incurs two structural limitations: i) the prefix's…

Large Language Models (LLMs) have driven significant progress, yet their growing parameter counts and context windows incur prohibitive compute, energy, and monetary costs. We introduce EfficientLLM, a novel benchmark and the first…

The computational difficulties of large language model (LLM) inference remain a significant obstacle to their widespread deployment. The need for many applications to support long input sequences and process them in large batches typically…

Efficiently handling long contexts in transformer-based language models with low perplexity is an active area of research. Numerous recent approaches like Linformer, Longformer, Performer, and Structured state space models (SSMs)., have not…

Large language models encounter critical GPU memory capacity constraints during long-context inference, where KV cache memory consumption severely limits decode batch sizes. While existing research has explored offloading KV cache to DRAM,…

The rapid evolution of Large Language Models (LLMs) towards long-context reasoning and sparse architectures has pushed memory requirements far beyond the capacity of individual device HBM. While emerging supernode architectures offer…

With the growing demand for long-context LLMs across a wide range of applications, the key-value (KV) cache has become a critical bottleneck for both latency and memory usage. Recently, KV-cache offloading has emerged as a promising…

The integration of long-context capabilities with visual understanding unlocks unprecedented potential for Vision Language Models (VLMs). However, the quadratic attention complexity during the pre-filling phase remains a significant…

Large language models (LLMs) based on transformers have made significant strides in recent years, the success of which is driven by scaling up their model size. Despite their high algorithmic performance, the computational and memory…

Large Language Models (LLMs) face significant computational challenges when processing long contexts due to the quadratic complexity of self-attention. While soft context compression methods, which map input text to smaller latent…

Transformer-based large language models (LLM) have been widely used in language processing applications. However, due to the memory constraints of the devices, most of them restrict the context window. Even though recurrent models in…