Related papers: L2C2: Last-Level Compressed-Cache NVM and a Proced…

Non-volatile memory (NVM) promises persistent main memory that remains correct despite loss of power. This has sparked a line of research into algorithms that can recover from a system crash. Since caches are expected to remain volatile,…

Existing key-value (KV) cache compression methods typically rely on heuristics, such as uniform cache allocation across layers or static eviction policies, however, they ignore the critical interplays among layer-specific feature patterns…

Lossy compression is one of the most efficient solutions to reduce storage overhead and improve I/O performance for HPC applications. However, existing parallel I/O libraries cannot fully utilize lossy compression to accelerate parallel…

Approaches for compressing large-language models using low-rank decomposition have made strides, particularly with the introduction of activation and loss-aware SVD, which improves the trade-off between decomposition rank and downstream…

Deployment of modern TinyML tasks on small battery-constrained IoT devices requires high computational energy efficiency. Analog In-Memory Computing (IMC) using non-volatile memory (NVM) promises major efficiency improvements in deep neural…

To mitigate the impact of noise and interference on multi-level-cell (MLC) flash memory with the use of low-density parity-check (LDPC) codes, we propose a dynamic write-voltage design scheme considering the asymmetric property of raw bit…

Most real-world problems that machine learning algorithms are expected to solve face the situation with 1) unknown data distribution; 2) little domain-specific knowledge; and 3) datasets with limited annotation. We propose Non-Parametric…

Long-context Large Language Model (LLM) inference faces increasing compute bottlenecks as attention calculations scale with context length, primarily due to the growing KV-cache transfer overhead that saturates High Bandwidth Memory (HBM).…

Image bitmaps have been widely used in in-memory applications, which consume lots of storage space and energy. Compared with legacy DRAM, non-volatile memories (NVMs) are suitable for bitmap storage due to the salient features in capacity…

DRAM-based memory is a critical factor that creates a bottleneck on the system performance since the processor speed largely outperforms the DRAM latency. In this thesis, we develop a low-cost mechanism, called ChargeCache, which enables…

We demonstrate that unstructured sparsity significantly improves KV cache compression for LLMs, enabling sparsity levels up to 70% without compromising accuracy or requiring fine-tuning. We conduct a systematic exploration of pruning…

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…

Key-Value (KV) Caching has become an essential technique for accelerating the inference speed and throughput of generative Large Language Models~(LLMs). However, the memory footprint of the KV cache poses a critical bottleneck in LLM…

Non-volatile memory (NVM) is an emerging technology, which has the persistence characteristics of large capacity storage devices(e.g., HDDs and SSDs), while providing the low access latency and byte-addressablity of traditional DRAM memory.…

Memory caches are being aggressively used in today's data-parallel systems such as Spark, Tez, and Piccolo. However, prevalent systems employ rather simple cache management policies--notably the Least Recently Used (LRU) policy--that are…

Emerging Non-Volatile Memories (NVMs) are promising contenders for building future memory systems. On the other side, unlike DRAM systems, NVMs can retain data even after power loss and thus enlarge the attack surface. While data encryption…

Spin-Transfer Torque RAM (STTRAM) is a promising alternative to SRAM in on-chip caches due to several advantages. These advantages include non-volatility, low leakage, high integration density, and CMOS compatibility. Prior studies have…

Large language models (LLM) have achieved remarkable performance across a wide range of tasks. However, their substantial parameter sizes pose significant challenges for deployment on edge devices with limited computational and memory…

Large Language Model (LLM) inference is increasingly constrained by memory bandwidth, with frequent access to the key-value (KV) cache dominating data movement. While attention sparsity reduces some memory traffic, the relevance of past…

Large Language Models (LLMs) have made remarkable progress in processing extensive contexts, with the Key-Value (KV) cache playing a vital role in enhancing their performance. However, the growth of the KV cache in response to increasing…