Tangram

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

05:21

2026-06-16

letsdatascience.com

large-language-models

Tangram hides GPU heterogeneity for LLM parallelization

Tangram, a system described in an arXiv paper submitted on 15 June 2026, hides GPU heterogeneity to allow existing LLM parallelizers to operate on heterogeneous clusters, reporting up to 2.3x higher t…

01:20

2026-06-06

arxiv.org

machine-learning

Unlocking Non-Uniform KV Cache for Efficient Multi-Turn LLM Serving

Researchers introduced Tangram, a serving system that enables non-uniform Key-Value cache compression for multi-turn large language model inference. The system uses deterministic budget allocation, he…

// co-occurs with top 4 entities

Metis 1 Sailor 1 arXiv 1 GPU 1

// topics top 5 topics

large language models 2 ai infrastructure 2 ai research 2 machine learning 1 neural networks 1