Related papers: DualPath: Breaking the Storage Bandwidth Bottlenec…

Recent large language models (LLMs) face increasing inference latency as input context length and model size continue to grow. In particular, the retrieval-augmented generation (RAG) technique, which enhances LLM responses by incorporating…

Distributed prefix caching accelerates long-context LLM serving by reusing KV cache entries for common context prefixes. However, KV cache fetches can become a bottleneck when network bandwidth is limited. Compression mitigates the…

The key-value (KV) cache is a foundational optimization in Transformer-based large language models (LLMs), eliminating redundant recomputation of past token representations during autoregressive generation. However, its memory footprint…

Batch inference for agentic workloads stresses the GPU key-value (KV) cache in a sustained and cumulative manner, often causing severe throughput degradation well before memory capacity is exhausted. We identify this phenomenon as…

Language models (LMs) underpin emerging mobile and embedded AI applications like meeting and video summarization and document analysis, which often require processing multiple long-context inputs. Running an LM locally on-device improves…

Compound AI systems, such as agentic systems, are an emerging trend in large-scale enterprise settings, with multiple LLMs specialized for different users, tasks, and/or roles working together. In these scenarios, different models often…

Transformer LLMs have been shown to exhibit strong reasoning ability that scales with inference-time compute, most prominently through token-space "thinking" chains of thought. A growing line of work pushes extra computation into the…

Large language model (LLM) based agentic workflows have become a popular paradigm for coordinating multiple specialized agents to solve complex tasks. To improve serving efficiency, existing LLM systems employ prefix caching to reuse…

Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…

Disaggregated inference has become an essential framework that separates the prefill (P) and decode (D) stages in large language model inference to improve throughput. However, the KV cache transfer faces significant delays between prefill…

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…

LLM inference powers latency-critical production services nowadays. The bursty nature of inference traffic results in over-provisioning, which in turn leads to resource underutilization. While online-offline colocation promises to utilize…

Production vLLM fleets typically provision each instance for the worst-case context length, leading to substantial KV-cache over-allocation and under-utilized concurrency. In practice, 80-95% of requests are short, yet are served under…

This paper presents a predictive deep learning framework for dynamic sub-band allocation in Sub-Band Full Duplex (SBFD) systems, addressing the challenge of balancing uplink (UL) and downlink (DL) performance under highly dynamic traffic…

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…

KV cache has traditionally been stored in GPU memory to accelerate the decoding phase of large language model (LLM) inference. However, it is increasingly necessary to move KV caches outside GPU devices, to enable cache reuse across…

The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing KV cache compression methods alleviate memory pressure, they…

Large language models (LLMs) are increasingly deployed in AI infrastructure, driving the need for high throughput, resource efficient serving systems. Disaggregated LLM serving, which separates prompt prefill from auto-regressive decode,…

Large Language Models (LLMs) are increasingly deployed in complex multi-agent applications that rely on external function calls. This workload creates severe performance challenges for the KV Cache: spatial contention leads to the eviction…

Memory-augmented Large Language Models (LLMs) have demonstrated remarkable capability for complex and long-horizon embodied planning. By keeping track of past experiences and environmental states, memory enables LLMs to maintain a global…