Related papers: OrbitFlow: SLO-Aware Long-Context LLM Serving with…

Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality).…

Large language models (LLMs) can now handle longer sequences of tokens, enabling complex tasks like book understanding and generating lengthy novels. However, the key-value (KV) cache required for LLMs consumes substantial memory as context…

Modern language agents must operate over long-horizon, multi-turn histories, yet deploying such agents with Small Language Models (SLMs) remains fundamentally difficult. Full-context prompting causes context overflow, flat retrieval exposes…

Large language models (LLMs) with different architectures and sizes have been developed. Serving each LLM with dedicated GPUs leads to resource waste and service inefficiency due to the varying demand of LLM requests. A common practice is…

Layerwise offloading reduces the GPU memory footprint of large diffusion transformer (DiT) inference by prefetching upcoming layers from host memory, but its effectiveness hinges on hiding prefetch latency behind per-layer computation. This…

The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent dynamic retrieval…

In production environments, large language model (LLM) serving is required to meet stringent service-level objectives (SLOs) amid highly variable request patterns. In practice, request lengths follow a long-tail distribution, which gives…

Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT reasoning process imposes substantial memory overhead due to…

We study offline scheduling for large language model (LLM) serving under a fixed KV-cache memory budget, where requests have heterogeneous prompt (prefill) and response (decode) lengths. Prompt tokens determine initial KV usage, and each…

The past few years has witnessed specialized large language model (LLM) inference systems, such as vLLM, SGLang, Mooncake, and DeepFlow, alongside rapid LLM adoption via services like ChatGPT. Driving these system design efforts is the…

Modern Large Language Model serving system batches multiple requests to achieve high throughput, while batching attention operations is challenging, rendering memory bandwidth a critical bottleneck. The community relies on high-end GPUs…

Long-context LLM serving is bottlenecked by the cost of attending over ever-growing KV caches. Dynamic sparse attention promises relief by accessing only a small, query-dependent subset of the KV state per decoding step and extending the KV…

This paper introduces SLOs-Serve, a system designed for serving multi-stage large language model (LLM) requests with application- and stage-specific service level objectives (SLOs). The key idea behind SLOs-Serve is to customize the…

Serving large language models (LLMs) is important for cloud providers, and caching intermediate results (KV\$) after processing each request substantially improves serving throughput and latency. However, there is limited understanding of…

Long-context Multimodal Large Language Models (MLLMs) demand substantial computational resources for inference as the growth of their multimodal Key-Value (KV) cache, in response to increasing input lengths, challenges memory and time…

As large language models (LLMs) take on complex tasks, their inputs are supplemented with longer contexts that incorporate domain knowledge. Yet using long contexts is challenging, as nothing can be generated until the whole context is…

Large Language Models are increasingly being deployed in datacenters. Serving these models requires careful memory management, as their memory usage includes static weights, dynamic activations, and key-value caches. While static weights…

Long context fine-tuning of large language models(LLMs) involves training on datasets that are predominantly composed of short sequences and a small proportion of longer sequences. However, existing approaches overlook this long-tail…

Inference on large-language models (LLMs) is constrained by GPU memory capacity. A sudden increase in the number of inference requests to a cloud-hosted LLM can deplete GPU memory, leading to contention between multiple prompts for limited…

In Large Language Model (LLM) serving, the KV-cache (KVC) bottleneck causes high tail Time-to-First-Token (TTFT) and Time-Between-Tokens (TBT), impairing user experience, particularly in time-sensitive applications. However, satisfying both…