Related papers: A First Look At Efficient And Secure On-Device LLM…

LLM inference exhibits substantial variability across queries and execution phases, yet inference configurations are often applied uniformly. We present a measurement-driven characterization of workload heterogeneity and energy-performance…

Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and bandwidth demands. This is because the key-value (KV) cache, an intermediate structure storing…

LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a…

Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving. Current systems suffer from three compounding inefficiencies: (1) the absence of unified KV cache…

Context lengths of Large Language Models (LLMs) have exploded in recent years, with 128k-token context becoming a standard and million-token context becoming a reality. Efficiently supporting long-context inference remains challenging as…

Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for…

In this work, we design and implement VQ-LLM, an efficient fused Vector Quantization (VQ) kernel generation framework. We first introduce a software abstraction called codebook cache to optimize codebook access efficiency and support the…

Large Language Model or LLM inference has two phases, the prompt (or prefill) phase to output the first token and the extension (or decoding) phase to the generate subsequent tokens. In this work, we propose an efficient parallelization…

Reducing the key-value (KV) cache burden in Large Language Models (LLMs) significantly accelerates inference. Dynamically selecting critical KV caches during decoding helps maintain performance. Existing methods use random linear hashing to…

When transformer-based language models are deployed for text generation, most of the inference time is spent in the decoding stage, where output tokens are generated sequentially. Reducing the hardware cost of each decoding step is…

Several works have developed eviction policies to remove key-value (KV) pairs from the KV cache for more efficient inference. The focus has been on compressing the KV cache after the input prompt has been processed for faster token…

Transformer-based large language models (LLMs) have demonstrated remarkable potential across a wide range of practical applications. However, long-context inference remains a significant challenge due to the substantial memory requirements…

Large Language Models (LLMs) have achieved remarkable progress across reasoning, generation, and decision-making tasks, yet deploying them on mobile, embedded, and edge devices remains particularly challenging. On-device LLM inference is…

We present LLMQ, an end-to-end CUDA/C++ implementation for medium-sized language-model training, e.g. 3B to 32B parameters, on affordable, commodity GPUs. These devices are characterized by low memory availability and slow communication…

The integration of Large Language Models (LLMs) into Electronic Design Automation (EDA) and hardware security is rapidly reshaping the semiconductor industry. While LLMs offer unprecedented capabilities in generating Register Transfer Level…

Key-Value cache (\texttt{KV} \texttt{cache}) compression has emerged as a promising technique to optimize Large Language Model (LLM) serving. It primarily decreases the memory consumption of \texttt{KV} \texttt{cache} to reduce the…

Large Language Models (LLMs) fine-tuning technologies have achieved remarkable results. However, traditional LLM fine-tuning approaches face significant challenges: they require large Floating Point (FP) computation, raising privacy…

Transformers have emerged as the underpinning architecture for Large Language Models (LLMs). In generative language models, the inference process involves two primary phases: prompt processing and token generation. Token generation, which…

SMEs increasingly seek alternatives to cloud LLM APIs, which raise data privacy concerns. Dedicated cloud GPU instances offer improved privacy but with limited guarantees and ongoing costs, while professional on-premise hardware (A100,…

Large Language Models (LLMs) have gained popularity in recent years, driving up the demand for inference. LLM inference is composed of two phases with distinct characteristics: a compute-bound prefill phase followed by a memory-bound decode…