We present the design and implementation of a new lifetime-aware tensor offloading framework for GPU memory expansion using low-cost PCIe-based solid-state drives (SSDs). Our framework, TERAIO, is developed explicitly for large language model (LLM) training with multiple GPUs and multiple SSDs. Its design is driven by our observation that the active tensors take only a small fraction (1.7% on average) of allocated GPU memory in each LLM training iteration, the inactive tensors are usually large and will not be used for a long period of time, creating ample opportunities for offloading/prefetching tensors to/from slow SSDs without stalling the GPU training process. TERAIO accurately estimates the lifetime (active period of time in GPU memory) of each tensor with the profiling of the first few iterations in the training process. With the tensor lifetime analysis, TERAIO will generate an optimized tensor offloading/prefetching plan and integrate it into the compiled LLM program via PyTorch. TERAIO has a runtime tensor migration engine to execute the offloading/prefetching plan via GPUDirect storage, which allows direct tensor migration between GPUs and SSDs for alleviating the CPU bottleneck and maximizing the SSD bandwidth utilization. In comparison with state-of-the-art studies such as ZeRO-Offload and ZeRO-Infinity, we show that TERAIO improves the training performance of various LLMs by 1.47 on average, and achieves 80.7% of the ideal performance assuming unlimited GPU memory.

Out-of-tree kernel patches are essential for adapting the Linux kernel to new hardware or enabling specific functionalities. Maintaining and updating these patches across different kernel versions demands significant effort from experienced engineers. Large language models (LLMs) have shown remarkable progress across various domains, suggesting their potential for automating out-of-tree kernel patch migration. However, our findings reveal that LLMs, while promising, struggle with incomplete code context understanding and inaccurate migration point identification. In this work, we propose MIGGPT, a framework that employs a novel code fingerprint structure to retain code snippet information and incorporates three meticulously designed modules to improve the migration accuracy and efficiency of out-of-tree kernel patches. Furthermore, we establish a robust benchmark using real-world out-of-tree kernel patch projects to evaluate LLM capabilities. Evaluations show that MIGGPT significantly outperforms the direct application of vanilla LLMs, achieving an average completion rate of 74.07%

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?

Large Language Model (LLM) agents are capable of task execution across various domains by autonomously interacting with environments and refining LLM responses based on feedback. However, existing model serving systems are not optimized for the unique demands of serving agents. Compared to classic model serving, agent serving has different characteristics: predictable request pattern, increasing quality requirement, and unique prompt formatting. We identify a key problem for agent serving: LLM serving systems lack session-awareness. They neither perform effective KV cache management nor precisely select the cheapest yet competent model in each round. This leads to a cost-quality tradeoff, and we identify an opportunity to surpass it in an agent serving system. To this end, we introduce AGSERVE for AGile AGent SERVing.

What does the data tell us about immigration in Wales? Like many countries, Wales sees a steady flow of people arriving and leaving for other countries each year. The difference between those arriving and those leaving is known as net migration. Focusing on people moving from abroad, latest estimates say Wales' population - which was 3.2 million in June 2024 - had increased by about 23,000 over the previous year as a result of net international migration. A recent YouGov poll found a quarter of people surveyed in Wales believed that immigration, alongside the economy, should be among the issues prioritised by the Welsh government, even though immigration is controlled by the UK government.

A quantum computer capable of breaking the encryption that secures the internet now seems to be just around the corner. Stunning revelations from two research teams outline how it could happen, with one suggesting that the current largest quantum machine is already more than halfway towards the size needed. The two studies concern an encryption technique built around the elliptic curve discrete logarithm problem (ECDLP). The particulars of how this mathematical problem is solved made it a good candidate for encrypting data and led to its widespread adoption for securing lots of internet communication, including bank transactions, and nearly every major cryptocurrency, including bitcoin. It is extremely difficult for conventional computers to crack ECDLP-based encryption, but since the 1990s researchers have known that quantum computers wouldn't have the same trouble.

Things to Do in L.A. Tap to enable a layout that focuses on the article. A renter drives a U-Haul in Mission Valley in 2023. This is read by an automated voice. Please report any issues or inconsistencies here . Anecdotal data suggest there is also an exodus of regular people who load their belongings into rental trucks and lug them to another state.

Mixture-of-Experts (MoE) models scale large language models through conditional computation, but inference becomes memory-bound once expert weights exceed the capacity of GPU memory. In this case, weights must be offloaded to external memory, and fetching them incurs costly and repeated transfers. We address this by adopting CXL-attached near-data processing (CXL-NDP) as the offloading tier to execute cold experts in place, converting expensive parameter movement into cheaper activation movement. Unlike prior GPU-NDP systems that are largely context-agnostic and reactive, we develop a context-aware MoE system that uses prefill-stage activation statistics to guide decoding-stage expert placement, dynamically pins hot experts in GPU-side HBM, and maps the remainder to CXL-NDP. To meet NDP's limited compute throughput, we introduce context-aware mixed-precision quantization that allocates per-expert bitwidths (1-4 bit) based on prefill stage. The resulting MoE inference system overlaps GPU and NDP execution while minimizing cross-device movement. The evaluation on the GPU-NDP system shows that our approach achieves up to an 8.7-fold decoding throughput improvement over the state-of-the-art method, while incurring only a 0.13% average accuracy drop.

Migrating a set of software variants into a software product line (SPL) is an expensive and potentially challenging endeavor. Indeed, SPL engineering can significantly impact a company's development process and often requires changes to established developer practices. The work presented in this paper stems from a collaboration with a Small and Medium-sized Enterprise (SME) that decided to migrate its existing code base into an SPL. In this study, we conducted an in-depth evaluation of the company's current development processes and practices, as well as the anticipated benefits and risks associated with the migration. Key stakeholders involved in software development participated in this evaluation to provide insight into their perceptions of the migration and their potential resistance to change. This paper describes the design of the interviews conducted with these stakeholders and presents an analysis of the results. Among the qualitative findings, we observed that all participants, regardless of their role in the development process, identified benefits of the migration relevant to their own activities. Furthermore, our results suggest that an effective risk mitigation strategy involves keeping stakeholders informed and engaged throughout the process, preserving as many good practices as possible, and actively involving them in the migration to ensure a smooth transition and minimize potential challenges.

Out-of-tree kernel patches are essential for adapting the Linux kernel to new hardware or enabling specific functionalities. Maintaining and updating these patches across different kernel versions demands significant effort from experienced engineers. Large language models (LLMs) have shown remarkable progress across various domains, suggesting their potential for automating out-of-tree kernel patch migration. However, our findings reveal that LLMs, while promising, struggle with incomplete code context understanding and inaccurate migration point identification. In this work, we propose MigGPT, a framework that employs a novel code fingerprint structure to retain code snippet information and incorporates three meticulously designed modules to improve the migration accuracy and efficiency of out-of-tree kernel patches. Furthermore, we establish a robust benchmark using real-world out-of-tree kernel patch projects to evaluate LLM capabilities. Evaluations show that MigGPT significantly outperforms the direct application of vanilla LLMs, achieving an average completion rate of 74.07 for migration tasks.