English(EN) KOSMOS: Self-scheduling Persistent Kernels for Communication-Compute Overlap

KOSMOS库将AMD GPU上的LLM训练速度提高了1.83倍

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-06 05:00

一个名为KOSMOS的新库已被开发出来，以提高在GPU上训练大型语言模型的效率。KOSMOS通过使用自调度持久性内核来优化Transformer层内的通信和计算阶段，这些内核会适应数据就绪情况。在AMD Instinct MI350X和MI355X GPU上进行评估时，与现有方法相比，KOSMOS在Megatron-LM、DeepSeek-V3和Qwen3-235B等模型上实现了1.10倍至1.83倍的显著加速。 AI

影响该库可以显著缩短LLM的训练时间并降低成本，从而使大型模型开发更加易于获得。

排序理由该集群描述了一个新库及其在arXiv论文中提出的性能评估。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一个新库及其在arXiv论文中提出的性能评估。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: infra, paper; 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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Alexander Magro, Aristotle Martin, Ye Wang, Wen Chen · 2026-11-06 05:00

KOSMOS: 用于通信-计算重叠的自调度持久性内核

arXiv:2611.07477v1 Announce Type: cross Abstract: Tensor and sequence parallelism (TP+SP) and expert parallelism (EP) put collectives on the critical path of transformer layers. State-of-the-art fused kernels mitigate this with fixed roles or schedules, but this rigidity leaves l…

本文如何被排名

报道来源 [1]

KOSMOS: 用于通信-计算重叠的自调度持久性内核

相关实体

相关话题