Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 15 of 15 for “"Cache Compression"”.
-
Combining inter and intra-line cache compression
Caches are essential to today's microprocessors. They close the huge speed gap between processors and memories. However, cache design presents an important tradeoff. A bigger cache size should increase performance and allow processors to perform faster, but it is also limited by its silicon, area, …
-
Pushing the limits of long context LLM inference via KV cache compression
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms
-
Low-rank KV cache compression in LLMs: A second-order output metric and its limits
The key–value (KV) cache makes autoregressive decoding in large language models fast, but it grows with the length of the context. At long context it becomes the main drain on a GPU’s memory, both in how much it has to store and in how fast it can be read. Compressing the keys and values with a …
-
End-to-End KV-Cache Materialization and Evaluation
… Time-to-First-Token (TTFT), making efficient KV-cache compression and reconstruction critical. This thesis presents QUARK, a data-invariant KV-cache compression method that exploits stable, layer-specific statistical patterns in KV-cache data. QUARK uses offline profiling to build model-specific …
-
Efficient in-hardware compression of on-chip data
… have not kept up: average CPU last-level cache capacity per core (thread) has stagnated at 1MB. Similar trends exist in special-purpose computing systems, with only up to tens of megabytes of on-chip memory available in most recent AI accelerators. In this dissertation, we explore …
-
Efficient shared cache management in multicore processors
… various resources (such as memory bandwidth and caches) are designed to be shared by concurrently running threads. Though it is good to be able to run multiple programs on a single chip at the same time, sometimes the contention of these shared resources can create problems for system …
-
Quantized Lookup Table-Based Representation for Key-Value Cache
… bottleneck: the transmission of Key-Value (KV) caches between devices to enable cache reuse. As the demand for long-context inference grows, KV caches can become extremely large, making efficient compression essential to reduce communication costs. Interestingly, we observe that KV caches …
-
Quantized Lookup Table-Based Representation for Key-Value Cache
… bottleneck: the transmission of Key-Value (KV) caches between devices to enable cache reuse. As the demand for long-context inference grows, KV caches can become extremely large, making efficient compression essential to reduce communication costs. Interestingly, we observe that KV caches …
-
Quantized Lookup Table-Based Representation for Key-Value Cache
… bottleneck: the transmission of Key-Value (KV) caches between devices to enable cache reuse. As the demand for long-context inference grows, KV caches can become extremely large, making efficient compression essential to reduce communication costs. Interestingly, we observe that KV caches …
-
Speculative Techniques for Memory Hierarchy Management
… architects have added multiple levels of cache to fill this gap, cache levels that are closer to the processors are smaller and faster. On the other hand, the levels that are far from the processors are bigger and slower. However the processors are still exposed to the latency of DRAM on …
-
Optimized Multi-Agent Defense Pipeline Against Advanced Prompt Injection Attacks
… the security layer behaves when the inference cache fills up. I designed a multi-agent defense pipeline with three architectural contributions. The first is a white-box adaptive adversary. It attacks all defense components at once through a joint-loss optimization. I evaluated it across five …
-
On the Efficiency and Steerability of Self-Attention Mechanism of Large Language Models
… compromising performance. Near-lossless KV cache compression for efficient generative inference. Generative inference in LLMs depends heavily on Key-Value (KV) caches, which can become memory-intensive as sequence length grows, leading to memory-bound inference and significantly reduced …
-
Flexible And Efficient Accelerator Architecture For Runtime Monitoring
Secure and reliable computing remains an open problem. Just in the past year, security vulnerabilities continued to be discovered in widely-used applications, and remote attacks that take advantage of these vulnerabilities can cause an enormous amount of damage. Runtime monitoring is a promising …
-
Byte-select compression
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-12-04 without embargo terms
-
High-performance memory system architectures using data compression
… this processor-memory performance gap is using compression in the memory hierarchy. In this thesis, to use compression techniques more efficiently, compressed cacheline size information is studied, and size-aware cache management techniques and hot-cacheline prediction for dynamic early …