Related papers: Challenges in Deploying Long-Context Transformers:…

Although large language models (LLMs) demonstrate impressive performance for many language tasks, most of them can only handle texts a few thousand tokens long, limiting their applications on longer sequence inputs, such as books, reports,…

We introduce the Block Transformer which adopts hierarchical global-to-local modeling to autoregressive transformers to mitigate the inference bottlenecks associated with self-attention. Self-attention requires the key-value (KV) cache of…

As language models support larger and larger context sizes, evaluating their ability to make effective use of that context becomes increasingly important. We analyze the ability of several code generation models to handle long range…

The expanding context windows in large language models (LLMs) have greatly enhanced their capabilities in various applications, but they also introduce significant challenges in maintaining low latency, particularly in Time to First Token…

We introduce Long-VITA, a simple yet effective large multi-modal model for long-context visual-language understanding tasks. It is adept at concurrently processing and analyzing modalities of image, video, and text over 4K frames or 1M…

LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a…

Existing benchmarks for evaluating long-context language models (LCLMs) primarily focus on long-context recall, requiring models to produce short responses based on a few critical snippets while processing thousands of irrelevant tokens. We…

Training large language models (LLMs) in the cloud faces growing memory bottlenecks due to the limited capacity and high cost of GPUs. While GPU memory offloading to CPU and NVMe has made large-scale training more feasible, existing…

While long-context inference is crucial for advancing large language model (LLM) applications, its prefill speed remains a significant bottleneck. Current approaches, including sequence parallelism strategies and compute reduction through…

Solving complex or long-horizon problems often requires large language models (LLMs) to use external tools and operate over a significantly longer context window. New LLMs enable longer context windows and support tool calling capabilities.…

Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by memory consumption. Constant-memory alternatives such as RNNs and SSMs compress history…

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…

Large language models (LLMs) have demonstrated exceptional capabilities in generating text, images, and video content. However, as context length grows, the computational cost of attention increases quadratically with the number of tokens,…

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 adoption of large language models (LLMs) has created significant challenges for efficient inference at scale. Unlike traditional workloads, LLM inference is constrained by both computation and the memory overhead of key-value (KV)…

Large Language Models (LLMs) are increasingly deployed in large-scale online services, enabling sophisticated applications. However, the computational overhead of generating key-value (KV) caches in the prefill stage presents a major…

Large Language Models (LLMs) with long context capabilities are integral to complex tasks in natural language processing and computational biology, such as text generation and protein sequence analysis. However, training LLMs directly on…

Large Language Models (LLMs) have ignited an innovative surge of AI applications, marking a new era of exciting possibilities equipped with extended context windows. However, hosting these models is cost-prohibitive mainly due to the…

Deploying long-context large language models (LLMs) is essential but poses significant computational and memory challenges. Caching all Key and Value (KV) states across all attention heads consumes substantial memory. Existing KV cache…

The evolution of large language models (LLMs) towards applications with ultra-long contexts faces challenges posed by the high computational and memory costs of the Transformer architecture. While existing sparse and linear attention…