22 accepted papers
Recent advances in large language models (LLMs) have intensified the need to deliver both rapid responses and high-quality outputs. More powerful models yield better results but incur higher inference latency, whereas smaller models are faster yet less capable. Recent work proposes balancing this la…
Reinforcement Learning (RL) has become pivotal for improving model capabilities yet suffers from rollout efficiency bottlenecks due to the long-tail response length distribution. While existing works mitigate the impact of long tails via prompt-level tail scheduling, we focus on the root source of i…
Diffusion Transformers (DiTs) are increasingly adopted for long-video generation, yet inference is dominated by the quadratic cost of 3D full attention. Sparse attention mitigates this bottleneck by exploiting *token-pair redundancy* and pruning query-key interactions. Nevertheless, its effectivenes…
With the rapid evolution of Large Language Models (LLMs), multi-round workflows, such as autonomous agents and iterative retrieval, have become increasingly prevalent. However, this raises hurdles for serving LLMs under prefill-decode (PD) disaggregation, a widely adopted paradigm that separates the…
The operational cost of serving large language models remains prohibitively high, largely due to extreme workload heterogeneity in production traffic. We observe that combining disaggregated inference with resource autoscaling enables fine-grained resource adjustment, allowing inference phases and o…
Serving Large Language Models (LLMs) can benefit immensely from parallelizing both the model and input requests across multiple devices, but incoming workloads exhibit substantial spatial and temporal heterogeneity. Spatially, workloads comprise heterogeneous requests with varying compute and memory…
Many advanced Large Language Model (LLM) applications require long-context processing, but the self-attention module becomes a bottleneck during the prefilling stage of inference due to its quadratic time complexity with respect to sequence length. Existing sparse attention methods accelerate attent…
To schedule LLM inference, the \textit{shortest job first} (SJF) principle is favorable by prioritizing requests with short output lengths to avoid head-of-line (HOL) blocking. Existing methods usually predict a single output length for each request to facilitate scheduling. We argue that such a \te…
Recent advancements in Large Language Models (LLMs) have led to increasingly diverse requests, accompanied with varying resource (compute and memory) demands to serve them. However, this in turn degrades the cost-efficiency of LLM serving as common practices primarily rely on homogeneous GPU resourc…
Recently, using large language models (LLMs) for data augmentation has led to considerable improvements in unsupervised sentence embedding models. However, existing methods encounter two primary challenges: limited data diversity and high data noise. Current approaches often neglect fine-grained kno…
Vertical federated learning (VFL) trains model when the features of data samples are scattered over multiple clients. To improve efficiency, a promising approach is to find a coreset of the data samples and use it as a smaller training set. However, existing methods produce a large coreset when ther…
Sequence labeling remains a significant challenge in low-resource, domain-specific scenarios, particularly for character-dense languages. Existing methods primarily focus on enhancing model comprehension and improving data diversity to boost performance. However, these approaches still struggle with
Split learning is a prominent framework for vertical federated learning, where multiple clients collaborate with a central server for model training by exchanging intermediate embeddings. Recently, it is shown that an adversarial server can exploit the intermediate embeddings to train surrogate mode
Mixture of Experts (MoE) is a widely used technique to expand model sizes for better model quality while maintaining the computation cost constant. In a nutshell, an MoE model consists of multiple experts in each model layer and routes the training tokens to only a fixed number of experts rather tha…
Generating high-quality long videos with Diffusion Transformers (DiTs) faces significant latency due to computationally intensive attention mechanisms. For instance, generating an 8s 720p video (110K tokens) with HunyuanVideo requires around 600 PFLOPs, with attention computations consuming about 50…
Due to the recent success of diffusion models, text-to-image generation is becoming increasingly popular and achieves a wide range of applications. Among them, text-to-image editing, or continuous text-to-image generation, attracts lots of attention and can potentially improve the quality of generat…
With the remarkable achievements of large language models (LLMs), the demand for fine-tuning and deploying LLMs in various downstream tasks has garnered widespread interest. Parameter-efficient fine-tuning techniques represented by LoRA and model quantization techniques represented by GPTQ and AWQ a…
Larger transformer models perform better on various downstream tasks but require more cost to scale up the model size. To efficiently enlarge models, the Mixture-of-Expert (MoE) architecture is widely adopted, which consists of a gate network and a series of experts and keep the training cost consta…
Transformer-based LLMs are becoming increasingly important in various AI applications. However, apart from the success of LLMs, the explosive demand of long context handling capabilities is a key and in-time problem for both academia and industry. Due to the limitations from the quadratic complexit…
Large-scale deep learning models contribute to significant performance improvements on varieties of downstream tasks. Current data and model parallelism approaches utilize model replication and partition techniques to support the distributed training of ultra-large models. However, directly deployin…
Vertical Federated Learning (VFL), that trains federated models over vertically partitioned data, has emerged as an important learning paradigm. However, existing VFL methods are facing two challenges: (1) scalability when # participants grows to even modest scale and (2) diminishing return w.r.t. #…
Recent years have witnessed intensive research interests on training deep neural networks (DNNs) more efficiently by quantization-based compression methods, which facilitate DNNs training in two ways: (1) activations are quantized to shrink the memory consumption, and (2) gradients are quantized to…