Related papers: Break the Sequential Dependency of LLM Inference U…

Distributed inference serves as a promising approach to enabling the inference of large language models (LLMs) at the network edge. It distributes the inference process to multiple devices to ensure that the LLMs can fit into the device…

Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. verification is $4\times$ slower than token generation when a…

Optimizing inference for long-context large language models (LLMs) is increasingly important due to the quadratic compute and linear memory cost of Transformers. Existing approximate inference methods, including key-value (KV) cache…

RAPID-LLM is a unified performance modeling framework for large language model (LLM) training and inference on GPU clusters. It couples a DeepFlow-based frontend that generates hardware-aware, operator-level Chakra execution traces from an…

Large Language Models (LLMs)-based text retrieval retrieves documents relevant to search queries based on vector similarities. Documents are pre-encoded offline, while queries arrive in real-time, necessitating an efficient online query…

As large language models (LLMs) scale up, accuracy improves, but the autoregressive (AR) nature of decoding increases latency since each token requires a serial forward pass. Speculative decoding addresses this by employing a fast drafter…

The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware…

AI accelerator processing capabilities and memory constraints largely dictate the scale in which machine learning workloads (e.g., training and inference) can be executed within a desirable time frame. Training a state of the art,…

Fine-tuning large language models (LLMs) for recommendation in a generative manner has delivered promising results, but encounters significant inference overhead due to autoregressive decoding in the language space. This work explores…

The computation and memory costs of large language models kept increasing over last decade, which reached over the scale of 1T parameters. To address the challenges from the large scale models, model compression techniques such as low-rank…

Vision-language models (VLMs) predominantly rely on autoregressive decoding, which generates tokens one at a time and fundamentally limits inference throughput. This limitation is especially acute in physical AI scenarios such as robotics…

Inference accounts for the majority of latency and energy consumption in large language model (LLM) deployments, often exceeding 90% of total cost. While training-time efficiency has seen extensive progress, runtime optimization remains a…

We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves state-of-the-art speedup for large language models (LLMs) inference. The performance gains are driven by three key aspects: (1) leveraging a…

Speculative decoding accelerates LLM inference by using a draft model to look ahead, but gains are capped by the cost of autoregressive draft generation: increasing draft size elevates acceptance rates but introduces additional latency…

Multiple heads decoding accelerates the inference of Large Language Models (LLMs) by predicting next several tokens simultaneously. It generates and verifies multiple candidate sequences in parallel via tree attention with a fixed…

We propose an acceleration scheme for large language models (LLMs) through Speculative Decoding with Semantic Adaptive Tokens (SDSAT). The primary objective of this design is to enhance the LLM model's ability to generate draft tokens more…

Vision-language models (VLMs) have demonstrated strong capabilities in multimodal perception and reasoning. However, deploying large VLMs on mobile devices remains challenging due to their substantial computational and memory demands. A…

Masked diffusion language models (MDLMs) enable parallel decoding by predicting all masked positions at each denoising step, yet existing training-free samplers usually decide which positions to commit at token-level granularity. We revisit…

Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex…

Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is enlarged. However, the batch size is limited by some…