Related papers: VerilogMonkey: Exploring Parallel Scaling for Auto…

Retrieval-Augmented Generation (RAG) couples document retrieval with large language models (LLMs). While scaling generators often improves accuracy, it also increases inference and deployment overhead. We study an orthogonal axis: enlarging…

Inference-time scaling via repeated sampling has shown promise in reasoning tasks, but its effectiveness in multilingual generation remains underexplored. We evaluate this approach using perplexity- and reward-based verifiers on two…

Traditionally, designs are written in Verilog hardware description language (HDL) and debugged by hardware engineers. While this approach is effective, it is time-consuming and error-prone for complex designs. Large language models (LLMs)…

LLM serving systems typically treat user prompts as monolithic inputs, optimizing inference through decoding tricks or inter-query batching. However, many real-world prompts contain latent semantic parallelism--decomposable structures where…

Scaling LLM vocabulary is often used to reduce input sequence length and alleviate attention's quadratic cost. Yet, current LLM architectures impose a critical bottleneck to this procedure: the output projection layer scales linearly with…

The use of large language models (LLMs) for automated code generation has emerged as a significant focus within AI research. As these pretrained models continue to evolve, their ability to understand and generate complex code structures has…

Hybrid parallelism techniques are essential for efficiently training large language models (LLMs). Nevertheless, current automatic parallel planning frameworks often overlook the simultaneous consideration of node heterogeneity and dynamic…

Inspired by the success of language models (LM), scaling up deep learning recommendation systems (DLRS) has become a recent trend in the community. All previous methods tend to scale up the model parameters during training time. However,…

The recent advancements of Small Language Models (SLMs) have opened new possibilities for efficient code generation. SLMs offer lightweight and cost-effective alternatives to Large Language Models (LLMs), making them attractive for use in…

Several methods exist today to accelerate Machine Learning(ML) or Deep-Learning(DL) model performance for training and inference. However, modern techniques that rely on various graph and operator parallelism methodologies rely on search…

Reasoning LLMs produce longer outputs, requiring speculative decoding drafters trained on extended sequences. Parallel drafting - predicting multiple tokens per forward pass - offers latency benefits over sequential generation, but training…

While most autoregressive LLMs are constrained to one-by-one decoding, diffusion LLMs (dLLMs) have attracted growing interest for their potential to dramatically accelerate inference through parallel decoding. Despite this promise, the…

Existing Speech Language Model (SLM) scaling analysis paints a bleak picture. It predicts that SLMs require much more compute and data compared to text, leading some to question the feasibility of training high-quality SLMs. However, modern…

Thinking Large Language Models (LLMs) generate explicit intermediate reasoning traces before final answers, potentially improving transparency, interpretability, and solution accuracy for code generation. However, the quality of these…

Many real-world problems involve massive amounts of data. Under these circumstances learning algorithms often become prohibitively expensive, making scalability a pressing issue to be addressed. A common approach is to perform sampling to…

Optimal multiple sequence alignment by dynamic programming, like many highly dimensional scientific computing problems, has failed to benefit from the improvements in computing performance brought about by multi-processor systems, due to…

Topic modeling is a very powerful technique in data analysis and data mining but it is generally slow. Many parallelization approaches have been proposed to speed up the learning process. However, they are usually not very efficient because…

Large Language Models (LLMs) have demonstrated great promise in generating code, especially when used inside an evolutionary computation framework to iteratively optimize the generated algorithms. However, in some cases they fail to…

Large Language Models (LLMs) can generate code, but can they generate fast code for complex, real-world software systems? In this study, we investigate this question using a dataset of 65 tasks mined from performance-critical open-source…

Vectorization is a powerful optimization technique that significantly boosts the performance of high performance computing applications operating on large data arrays. Despite decades of research on auto-vectorization, compilers frequently…