Related papers: Optimus: Elastic Decoding for Efficient Diffusion …

Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving systems where hundreds of adapters must be hosted concurrently. While prior work has…

Speculative decoding is a standard method for accelerating the inference speed of large language models. However, scaling it for production environments poses several engineering challenges, including efficiently implementing different…

Large language models (LLMs) have demonstrated significant potential in code generation tasks. However, there remains a performance gap between open-source and closed-source models. To address this gap, existing approaches typically…

Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models. Recently, a new paradigm has emerged in the form of diffusion-based Large Language Models (dLLMs), which generate text by iteratively denoising masked…

Speculative decoding is a powerful way to accelerate autoregressive large language models (LLMs), but directly porting it to vision-language models (VLMs) faces unique systems constraints: the prefill stage is dominated by visual tokens…

Autoregressive (AR) generation is the standard decoding paradigm for Large Language Models (LLMs), but its token-by-token nature limits parallelism at inference time. Diffusion Language Models (DLLMs) offer parallel decoding by recovering…

Serving Large Language Models (LLMs) in production faces significant challenges from highly variable request patterns and severe resource fragmentation in serverless clusters. Current systems rely on static pipeline configurations that…

The Large Language Model (LLM) is widely employed for tasks such as intelligent assistants, text summarization, translation, and multi-modality on mobile phones. However, the current methods for on-device LLM deployment maintain slow…

Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) models, offering advantages such as accelerated parallel decoding and bidirectional context modeling. However, the vanilla…

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction. However, practical dLLM decoding still suffers from high inference latency, which limits…

Large Language Models (LLMs) are rapidly becoming critical infrastructure for enterprise applications, driving unprecedented demand for GPU-based inference services. A key operational challenge arises from the two-phase nature of LLM…

The past few years have witnessed a growing interest in LLM-based recommender systems (RSs), although their industrial deployment remains in a preliminary stage. Most existing deployments leverage LLMs offline as feature enhancers,…

Diffusion-based decoding has recently emerged as an appealing alternative to autoregressive (AR) generation, offering the potential to update multiple tokens in parallel and reduce latency. However, diffusion vision language models (dVLMs)…

We propose a new finetuning method to provide pre-trained large language models (LMs) the ability to scale test-time compute through the diffusion framework. By increasing the number of diffusion steps, we show our finetuned models achieve…

The rapid evolution and widespread adoption of generative large language models (LLMs) have made them a pivotal workload in various applications. Today, LLM inference clusters receive a large number of queries with strict Service Level…

LLM inference must meet strict latency SLOs (e.g., 100 ms P99 time-between-tokens) while maximizing goodput. Yet, real-world variability in prompt and response lengths skews compute-intensive prefill and memory-bound decode phases, making…

Training Large Language Models(LLMs) is one of the most compute-intensive tasks in high-performance computing. Predicting end-to-end training time for multi-billion parameter models distributed across hundreds of GPUs remains challenging…

Two widely adopted techniques for LLM inference serving systems today are hybrid batching and disaggregated serving. A hybrid batch combines prefill and decode tokens of different requests in the same batch to improve resource utilization…

Deploying large language models (LLMs) on edge devices is crucial for delivering fast responses and ensuring data privacy. However, the limited storage, weight, and power of edge devices make it difficult to deploy LLM-powered applications.…

Large language models (LLMs) are useful in many NLP tasks and become more capable with size, with the best open-source models having over 50 billion parameters. However, using these 50B+ models requires high-end hardware, making them…