Related papers: Communication Compression for Tensor Parallel LLM …
Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications, from search and recommendation systems to generative tasks. Although scaling laws indicate that larger models generally…
The rapid growth in the size of large language models has necessitated the partitioning of computational workloads across accelerators such as GPUs, TPUs, and NPUs. However, these parallelization strategies incur substantial data…
Augmenting large language models (LLMs) with auxiliary tokens has emerged as a promising strategy for enhancing model performance. In this work, we introduce a lightweight method termed latent tokens; these are dummy tokens that may be…
Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision, language, and video understanding tasks, scaling them to long-form speech remains a critical bottleneck due to the explosive growth of…
Federated learning (FL) has been extensively studied as a privacy-preserving training paradigm. Recently, federated block coordinate descent scheme has become a popular option in training large-scale models, as it allows clients to train…
Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately:…
Large language model inference is both memory-intensive and time-consuming, often requiring distributed algorithms to efficiently scale. Various model parallelism strategies are used in multi-gpu training and inference to partition…
Large Language Models (LLMs) and other large foundation models have achieved noteworthy success, but their size exacerbates existing resource consumption and latency challenges. In particular, the large-scale deployment of these models is…
In recent years, the compression of large language models (LLMs) has emerged as a key problem in facilitating LLM deployment on resource-limited devices, reducing compute costs, and mitigating the environmental footprint due to large-scale…
The rapid advancement in large foundation models is propelling the paradigm shifts across various industries. One significant change is that agents, instead of traditional machines or humans, will be the primary participants in the future…
Repository-level code intelligence tasks require large language models (LLMs) to process long, multi-file contexts. Such inputs introduce three challenges: crucial context can be obscured by noise, truncated due to limited windows, and…
Although large language models (LLM) have achieved remarkable performance, their enormous parameter counts hinder deployment on resource-constrained hardware. Low-rank compression can reduce both memory usage and computational demand, but…
The performance and efficiency of distributed machine learning (ML) depends significantly on how long it takes for nodes to exchange state changes. Overly-aggressive attempts to reduce communication often sacrifice final model accuracy and…
Tokenizer is an essential component for large language models (LLMs), and a tokenizer with a high compression rate can improve the model's representation and processing efficiency. However, the tokenizer cannot ensure high compression rate…
The autoregressive nature of conventional large language models (LLMs) inherently limits inference speed, as tokens are generated sequentially. While speculative and parallel decoding techniques attempt to mitigate this, they face…
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…
Prompt compression methods enhance the efficiency of Large Language Models (LLMs) and minimize the cost by reducing the length of input context. The goal of prompt compression is to shorten the LLM prompt while maintaining a high generation…
We propose a novel class of language models, Latent Thought Models (LTMs), which incorporate explicit latent thought vectors that follow an explicit prior model in latent space. These latent thought vectors guide the autoregressive…
Long-context inputs in large language models (LLMs) often suffer from the "lost in the middle" problem, where critical information becomes diluted or ignored due to excessive length. Context compression methods aim to address this by…
Recent research has demonstrated the feasibility of training efficient intent detectors based on pre-trained language model~(PLM) with limited labeled data. However, deploying these detectors in resource-constrained environments such as…