PulseAugur
中
实时 14:15:45
English(EN) HCRMap: Pressure-Aware Hot-Expert Residency Mapping for 3.5D MoE Chiplet Inference

新的HCRMap框架优化了3.5D片上系统中MoE大语言模型的推理

作者 PulseAugur 编辑部 · [3 个来源] ·

一篇新研究论文介绍了一种名为HCRMap的框架，该框架旨在优化3.5D片上系统上混合专家（MoE）大语言模型的推理。HCRMap通过动态管理不同内存层级的专家副本，解决了专家热度倾斜问题（即某些专家接收到的token数量不成比例）。这种方法旨在缓解通信、内存带宽和执行队列中的瓶颈。实验表明，与Hydra++、MoEntwine和PIMoE等现有方法相比，HCRMap显著降低了端到端延迟。 AI

影响 这项研究可能有助于在专用硬件架构上实现更高效、更快速的大语言模型推理。

排序理由 该集群包含一篇详细介绍用于优化AI模型推理的新框架的研究论文。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新的HCRMap框架优化了3.5D片上系统中MoE大语言模型的推理

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群包含一篇详细介绍用于优化AI模型推理的新框架的研究论文。
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
87 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [3]

  1. arXiv cs.AI TIER_1 English(EN) · Yongqin Zhang ·

    HCRMap：面向 3.5D MoE 芯片推理的压力感知热专家驻留映射

    arXiv:2607.11586v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) large language models (LLM) activate only a small number of experts during inference, but token routing introduces persistent expert hotness skew: a small set of hot experts continuously receives most tokens…

  2. arXiv cs.AI TIER_1 English(EN) · Yongqin Zhang ·

    HCRMap：面向 3.5D MoE 芯片推理的压力感知热专家驻留映射

    Mixture-of-Experts (MoE) large language models (LLM) activate only a small number of experts during inference, but token routing introduces persistent expert hotness skew: a small set of hot experts continuously receives most tokens, while the remaining experts are lightly loaded…

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

    HCRMap：面向 3.5D MoE 芯片推理的压力感知热专家驻留映射

    Mixture-of-Experts (MoE) large language models (LLM) activate only a small number of experts during inference, but token routing introduces persistent expert hotness skew: a small set of hot experts continuously receives most tokens, while the remaining experts are lightly loaded…

相关实体

相关话题