Related papers: PipeLive: Efficient Live In-place Pipeline Paralle…

Static-graph LLM decoders provide predictable launches, fixed tensor shapes, and low submission overhead, but online decoding exposes highly irregular KV-cache behavior: request lengths differ, EOS events arrive asynchronously, and logical…

We propose XPipe, an efficient asynchronous pipeline model parallelism approach for multi-GPU DNN training. XPipe is designed to use multiple GPUs to concurrently and continuously train different parts of a DNN model. To improve GPU…

Efficiently serving large language models (LLMs) requires batching of many requests to reduce the cost per request. Yet, with larger batch sizes and longer context lengths, the key-value (KV) cache, which stores attention keys and values to…

Key-value (KV) caching is critical for efficient inference in large language models (LLMs), yet its memory footprint scales linearly with context length, resulting in a severe scalability bottleneck. Existing approaches largely treat KV…

The rapid growth in machine learning models, especially in natural language processing and computer vision, has led to challenges when running these models on hardware with limited resources. This paper introduces Superpipeline, a new…

KV cache accelerates LLM inference by avoiding redundant computation, at the expense of memory. To support larger KV caches, prior work extends GPU memory with CPU memory via CPU-offloading. This involves swapping KV cache between GPU and…

The high memory and computation demand of large language models (LLMs) makes them challenging to be deployed on consumer devices due to limited GPU memory. Offloading can mitigate the memory constraint but often suffers from low GPU…

LLM serving is increasingly dominated by decode attention, which is a memory-bound operation due to massive KV cache loading from global memory. Meanwhile, real-world workloads exhibit substantial, hierarchical shared prefixes across…

KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empirically. Existing systems rely on average-case robustness, with no mechanism to detect or…

Modern hardware compilers increasingly rely on rich intermediate representations (IRs) to preserve optimization-relevant semantics before generating RTL code. However, one important optimization is still largely deferred to backend tools:…

Edge deployment of large language models (LLMs) can reduce latency for interactive services, but mobility introduces service interruptions when an user equipment (UE) hands over between base stations (BSs). To promptly resume decoding, the…

Large language models (LLMs) have gained great success in various domains. Existing systems cache Key and Value within the attention block to avoid redundant computations. However, the size of key-value cache (KV cache) is unpredictable and…

Multi-agent systems increasingly orchestrate multiple specialized language models to solve complex real-world problems, often invoking them over a shared context. This execution pattern repeatedly processes the same prompt prefix across…

High-throughput inference serving is essential for applications built on large language models (LLMs). Existing serving frameworks reduce request-level and batch-level bubbles through batching and scheduling, but often overlook bubbles…

Long-context Large Language Models (LLMs) face significant memory bottlenecks during inference due to the linear growth of key-value (KV) cache with sequence length. While individual optimization techniques like KV cache quantization,…

The increasing deployment of Large Language Model (LLM) inference on edge AI systems demands efficient execution under tight memory budgets. A key challenge arises from Key-Value (KV) caches, which often exceed available device memory.…

Diffusion-based generation is increasingly powering production content pipelines; however, deploying these models at scale remains a significant challenge. Model weights frequently exceed the memory capacity of commodity GPUs, while the…

Aggressively quantized large language models (LLMs), such as BitNet-style 1.58-bit Transformers with ternary weights, make it feasible to deploy generative AI on low-power edge FPGAs. However, as prompts grow to tens of thousands of tokens,…

LLM-based workflows compose specialized agents to execute complex tasks, and these agents usually share substantial context, allowing KV-Cache reuse to save computation. Existing approaches either manage KV-Cache at agent level and fail to…

Modern LLM serving systems must sustain high throughput while meeting strict latency SLOs across two distinct inference phases: compute-intensive prefill and memory-bound decode phases. Existing approaches either (1) aggregate both phases…