Related papers: Clover: Regressive Lightweight Speculative Decodin…

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

Video large language models (Vid-LLMs) have shown strong capabilities in understanding video content. However, their reliance on dense video token representations introduces substantial memory and computational overhead in both prefilling…

Speculative Decoding (SD) has emerged as a premier technique for accelerating Large Language Model (LLM) inference by decoupling token generation into rapid drafting and parallel verification. While recent advancements in self-speculation…

Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost: larger models offer superior capabilities but incur significant latency, while smaller models are faster but less powerful. Existing…

The proliferation of long-context large language models (LLMs) exposes a key bottleneck: the rapidly expanding key-value cache during decoding, which imposes heavy memory and latency costs. While recent approaches attempt to alleviate this…

The expansion of context windows in large language models (LLMs) to multi-million tokens introduces severe memory and compute bottlenecks, particularly in managing the growing Key-Value (KV) cache. While Compute Express Link (CXL) enables…

Speculative decoding has become a widely adopted technique for accelerating large language model (LLM) inference by drafting multiple candidate tokens and verifying them with a target model in parallel. Its efficiency, however, critically…

The Key-Value (KV) cache in generative large language models (LLMs) introduces substantial memory overhead. Existing works mitigate this burden by offloading or compressing the KV cache. However, loading the entire cache incurs significant…

Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static drafting lengths and rigid…

Large Language Model (LLM) inference uses an autoregressive manner to generate one token at a time, which exhibits notably lower operational intensity compared to earlier Machine Learning (ML) models such as encoder-only transformers and…

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…

Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities. However, the practical inference speed of open-sourced Diffusion LLMs often lags behind…

Continuous visual autoregressive (AR) models have demonstrated promising performance in image generation. However, the heavy autoregressive inference burden imposes significant overhead. In Large Language Models (LLMs), speculative decoding…

Large language models (LLMs) have achieved remarkable success in natural language tasks, but their inference incurs substantial computational and memory overhead. To improve efficiency, parallel decoding methods like Skeleton-of-Thought…

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…

Speculative decoding is a widely used technique for accelerating inference in large language models (LLMs), but its performance degrades as input length grows, with significant drops even at moderate lengths. Yet, this early degradation has…

This tutorial presents a comprehensive introduction to Speculative Decoding (SD), an advanced technique for LLM inference acceleration that has garnered significant research interest in recent years. SD is introduced as an innovative…

Efficient LLM inference on resource-constrained devices presents significant challenges in compute and memory utilization. Due to limited GPU memory, existing systems offload model weights to CPU memory, incurring substantial I/O overhead…

Speculative decoding accelerates autoregressive inference by drafting candidate tokens with a fast model and verifying them in parallel with the target. Self-speculative methods avoid the need for an external drafter but have been studied…

Large language models (LLM) have recently attracted surging interest due to their outstanding capabilities across various domains. However, enabling efficient LLM inference is challenging due to its autoregressive decoding that generates…