Related papers: Not All Thoughts Need HBM: Semantics-Aware Memory …

Long-context inference in Large Language Models (LLMs) is bottlenecked by the linear growth of Key-Value (KV) cache memory. Existing KV cache compression paradigms are fundamentally limited by heuristics: heuristic budgeting relies on…

Autoregressive decoding in large language models (LLMs) requires caching a growing list of past key-value (KV) pairs, making long-context inference a memory-bound problem. While recent methods have explored quantizing the cache, evicting…

While Key-Value (KV) cache compression is essential for efficient LLM inference, current evaluations disproportionately focus on sparse retrieval tasks, potentially masking the degradation of High-Density Reasoning where Chain-of-Thought…

Key-Value (KV) Caching has become an essential technique for accelerating the inference speed and throughput of generative Large Language Models~(LLMs). However, the memory footprint of the KV cache poses a critical bottleneck in LLM…

Extended reasoning in large language models (LLMs) creates severe KV cache memory bottlenecks. Leading KV cache compression methods estimate KV importance using attention scores from recent post-RoPE queries. However, queries rotate with…

Large language models (LLMs) show strong reasoning abilities but often produce unnecessarily long explanations that reduce efficiency. Although reinforcement learning (RL) has been used to improve reasoning, most methods focus on accuracy…

Reasoning-capable large language models solve hard problems by emitting long chains of thought, paying heavily in latency, GPU time, and energy. Casual inspection of their traces reveals extensive reformulation, verification, and circular…

Large reasoning models (LRMs) achieve strong accuracy through test-time scaling, generating longer chains of thought or sampling multiple solutions, but at steep costs in tokens and latency. We argue that memory is a core ingredient for…

Large language models (LLMs) can perform reasoning computations both internally within their latent space and externally by generating explicit token sequences like chains of thought. Significant progress in enhancing reasoning abilities…

Large Language Models (LLMs) have achieved remarkable progress across reasoning, generation, and decision-making tasks, yet deploying them on mobile, embedded, and edge devices remains particularly challenging. On-device LLM inference is…

As context windows in LLMs scale to 100K+ tokens, the key-value (KV) cache becomes the dominant memory bottleneck, with recent methods claiming 80-90% savings and minimal benchmark degradation. We argue these evaluations miss a structural…

Scaling inference for large language models (LLMs) is increasingly constrained by limited GPU memory, especially due to growing key-value (KV) caches required for long-context generation. While existing approaches offload KV caches to CPU…

In multimodal large language models (MLLMs), the surge of visual tokens significantly increases the inference time and computational overhead, making them impractical for real-time or resource-constrained applications. Visual token pruning…

In Large Language Model (LLM) inference, Key-Value (KV) caches (KV-caches) are essential for reducing time complexity. However, they result in a linear increase in GPU memory as the context length grows. While recent work explores KV-cache…

Large Language Models (LLMs) are now integral across various domains and have demonstrated impressive performance. Progress, however, rests on the premise that benchmark scores are both accurate and reproducible. We demonstrate that the…

High-performance GPU kernels are essential for efficient LLM deployment, yet optimizing them remains expertise-intensive. Recent LLM-based code generation makes automatic GPU operator generation promising, but operator optimization remains…

Reasoning, the process of devising and executing complex goal-oriented action sequences, remains a critical challenge in AI. Current large language models (LLMs) primarily employ Chain-of-Thought (CoT) techniques, which suffer from brittle…

Reasoning models have demonstrated impressive performance in self-reflection and chain-of-thought reasoning. However, they often produce excessively long outputs, leading to prohibitively large key-value (KV) caches during inference. While…

Large Language Models (LLMs) perform well on reasoning benchmarks but often fail when inputs alter slightly, raising concerns about the extent to which their success relies on memorization. This issue is especially acute in Chain-of-Thought…

Large language models (LLMs) have demonstrated impressive reasoning capabilities by scaling test-time compute via long Chain-of-Thought (CoT). However, recent findings suggest that raw token counts are unreliable proxies for reasoning…