Related papers: Beluga: A CXL-Based Memory Architecture for Scalab…
Compute eXpress Link (CXL) has emerged as a key enabler of memory disaggregation for future heterogeneous computing systems to expand memory on-demand and improve resource utilization. However, CXL is still in its infancy stage and lacks…
The growing prevalence of data-intensive workloads, such as artificial intelligence (AI), machine learning (ML), high-performance computing (HPC), in-memory databases, and real-time analytics, has exposed limitations in conventional memory…
Large Language Model (LLM) serving is increasingly constrained by the growing size of the key-value (KV) cache, which scales with both context length and generation length. Prior work shows that attention is dominated by a small subset of…
Host-GPU data movement has become a latency-critical bottleneck in LLM serving, surfacing in common paths such as model-weight movement and KV cache offload/fetch. Today, each host-GPU copy is effectively confined to the PCIe path of the…
Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex…
Transformer-based large language models (LLMs) have already achieved remarkable results on long-text tasks, but the limited GPU memory (VRAM) resources struggle to accommodate the linearly growing demand for key-value (KV) cache as the…
The high memory demands of the Key-Value (KV) Cache during the inference of Large Language Models (LLMs) severely restrict their deployment in resource-constrained platforms. Quantization can effectively alleviate the memory pressure caused…
In modern GPU inference, cache efficiency remains a major bottleneck, and heuristic policies such as \textsc{LRU} can perform far worse than the offline optimum. Existing learning-based caching systems improve hit rates mainly through…
Even with generational improvements in DRAM technology, memory access latency still remains the major bottleneck for application accelerators, primarily due to limitations in memory interface IPs which cannot fully account for variations in…
The rapid adoption of large language models (LLMs) has created significant challenges for efficient inference at scale. Unlike traditional workloads, LLM inference is constrained by both computation and the memory overhead of key-value (KV)…
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…
Recently the generative Large Language Model (LLM) has achieved remarkable success in numerous applications. Notably its inference generates output tokens one-by-one, leading to many redundant computations. The widely-used KV-Cache…
Heterogeneous memory technologies are increasingly important instruments in addressing the memory wall in HPC systems. While most are deployed in single node setups, CXL.mem is a technology that implements memories that can be attached to…
Large Language Models (LLMs) are becoming increasingly data-intensive due to growing model sizes, and they are becoming memory-bound as the context length and, consequently, the key-value (KV) cache size increase. Inference, particularly…
Vision-Language Models (VLMs) have emerged as a critical and fast-growing extension of Large Language Models (LLMs) that enable multimodal reasoning through both text and image inputs. Although VLMs enrich the capabilities of language…
Upcoming CXL-based disaggregated memory devices feature special purpose units to offload compute to near-memory. In this paper, we explore opportunities for offloading compute to general purpose cores on CXL memory devices, thereby enabling…
Large Language Models (LLMs) with expanding context windows face significant performance hurdles. While caching key-value (KV) states is critical for avoiding redundant computation, the storage footprint of long-context caches quickly…
Large Language Models (LLMs) increasingly require processing long text sequences, but GPU memory limitations force difficult trade-offs between memory capacity and bandwidth. While HBM-based acceleration offers high bandwidth, its capacity…
The increasing adoption of large language models (LLMs) necessitates inference serving systems that can deliver both high throughput and low latency. Deploying LLMs with hundreds of billions of parameters on memory-constrained GPUs exposes…
In recommendation systems, practitioners observed that increase in the number of embedding tables and their sizes often leads to significant improvement in model performances. Given this and the business importance of these models to major…