Related papers: K-Search: LLM Kernel Generation via Co-Evolving In…

Despite deep learning's success in chemistry, its impact is hindered by a lack of interpretability and an inability to resolve activity cliffs, where minor structural nuances trigger drastic property shifts. Current representation learning,…

As the Large Language Model (LLM) becomes increasingly important in various domains. However, the following challenges still remain unsolved in accelerating LLM inference: (1) Synchronized partial softmax update. The softmax operation…

Large language models (LLMs) have garnered significant attention for their superior performance in many knowledge-driven applications on the world wide web.These models are designed to train hundreds of millions or more parameters on large…

Generating texts with a large language model (LLM) consumes massive amounts of memory. Apart from the already-large model parameters, the key/value (KV) cache that holds information about previous tokens in a sequence can grow to be even…

Decision trees are a crucial class of models offering robust predictive performance and inherent interpretability across various domains, including healthcare, finance, and logistics. However, current tree induction methods often face…

Efficient branching policies are essential for accelerating Mixed Integer Linear Programming (MILP) solvers. Their design has long relied on hand-crafted heuristics, and now machine learning has emerged as a promising paradigm to automate…

Retrieval-augmented generation improves large language models by grounding outputs in external knowledge sources, reducing hallucinations and addressing knowledge cutoffs. However, standard embedding-based retrieval fails to capture the…

Automated heuristic design (AHD) has gained considerable attention for its potential to automate the development of effective heuristics. The recent advent of large language models (LLMs) has paved a new avenue for AHD, with initial efforts…

Multimodal Large Language Models (MLLMs) in real-world applications require access to external knowledge sources and must remain responsive to the dynamic and ever-changing real-world information in order to address information-seeking and…

In the last decade, a considerable research effort has been devoted to developing adaptive algorithms based on kernel functions. One of the main features of these algorithms is that they form a family of universal approximation techniques,…

Classic AI planning problems have been revisited in the Large Language Model (LLM) era, with a focus of recent benchmarks on success rates rather than plan efficiency. We examine the degree to which frontier models reason optimally versus…

In practical optimisation the dominant characteristics of the problem are often not known prior. Therefore, there is a need to develop general solvers as it is not always possible to tailor a specialised approach to each application. The…

Combinatorial optimization (CO) is essential for improving efficiency and performance in engineering applications. As complexity increases with larger problem sizes and more intricate dependencies, identifying the optimal solution become…

Large Language Models (LLMs) can exhibit considerable variation in the quality of their sampled outputs. Reranking and selecting the best generation from the sampled set is a popular way of obtaining strong gains in generation quality. In…

Finetuning large language models (LLMs) is essential for task adaptation, yet today's serving stacks isolate inference and finetuning on separate GPU clusters -- wasting resources and under-utilizing hardware. We introduce FlexLLM, the…

Document retrieval is a key stage of standard Web search engines. Existing dual-encoder dense retrievers obtain representations for questions and documents independently, allowing for only shallow interactions between them. To overcome this…

Making deep learning recommendation model (DLRM) training and inference fast and efficient is important. However, this presents three key system challenges - model architecture diversity, kernel primitive diversity, and hardware generation…

Recent progress in Large Language Models (LLMs) has opened new avenues for solving complex optimization problems, including Neural Architecture Search (NAS). However, existing LLM-driven NAS approaches rely heavily on prompt engineering and…

We develop a dynamic dictionary data structure for the GPU, supporting fast insertions and deletions, based on the Log Structured Merge tree (LSM). Our implementation on an NVIDIA K40c GPU has an average update (insertion or deletion) rate…

The integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) has significantly advanced Knowledge Graph Question Answering (KGQA). However, existing LLM-driven KGQA systems act as stateless planners, generating…