arXiv:2606. 18023v1 Announce Type: cross Abstract: Looped Transformers scale latent computation by repeatedly applying shared blocks, but sequential looping increases latency and KV-cache memory with the loop count.
arXiv:2607. 15456v1 Announce Type: new Abstract: Looped, weight-tied Transformers reduce parameters by reusing a block, but decoding still stores a separate K/V cache for every recurrence step.
arXiv:2606. 04438v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) and looped architectures scale models along two orthogonal axes, namely parameter capacity and effective depth.
arXiv:2606. 04023v1 Announce Type: cross Abstract: While large language models (LLMs) have been extensively evaluated on code generation tasks for general-purpose programming and GPU-accelerated environments (e.
arXiv:2505. 11480v4 Announce Type: replace-cross Abstract: Superoptimization is the task of transforming a program into a faster one, and ideally the very fastest possible one, while preserving its input-output behavior.
arXiv:2511. 08577v3 Announce Type: replace-cross Abstract: Improving the reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications.
arXiv:2511. 15503v3 Announce Type: replace-cross Abstract: High-performance Host processors can integrate Processing-In-Memory (PIM) devices, which can accelerate memory-intensive kernels of Machine Learning (ML) models, including Large Language Models (LLMs), by leveraging the large memory bandwidth available at PIM cores.
arXiv:2607. 19653v1 Announce Type: cross Abstract: Large language model (LLM) agents now perform well on correctness-oriented repository-level tasks, including SWE-Bench issue resolution and feature implementation in real codebases.
arXiv:2606. 02963v1 Announce Type: new Abstract: Production inference increasingly targets a heterogeneous mix of accelerators.
arXiv:2606. 10935v1 Announce Type: cross Abstract: Large language model inference is bottlenecked by autoregressive decoding, where each token requires a full forward pass.
Software performance optimization is a notoriously complex and manual task. Despite the growing use of Large Language Models (LLMs) for code refinement, we still lack benchmarks that capture how optimization actually happens in real-world codebases.
arXiv:2604. 26968v2 Announce Type: replace-cross Abstract: Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving.
arXiv:2607. 28418v1 Announce Type: cross Abstract: Pruning is a promising approach for improving the efficiency of LLMs.