THUDM

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

12:00

2026-06-17

github.com

large-language-models

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Researchers released IndexCache, a patch for SGLang and vLLM that accelerates sparse attention in DeepSeek-V3.2 and GLM-5 models by reusing index computations across layers, achieving up to 1.82× pref…

00:10

2026-06-14

dev.to

large-language-models

GLM 5.2 Just Dropped: What Zhipu's New Open-Weights Flagship Means for Developers

Zhipu AI (THUDM) released GLM 5.2, the latest open-weights flagship model, announced by Jie Tang on Twitter. The release includes weights, inference code, and a technical report on Hugging Face, with …

// co-occurs with top 8 entities

DeepSeek 2 SGLang 1 vLLM 1 DeepSeek-V3.2 1 GLM-5 1 Zhipu AI 1 GLM 5.2 1 Jie Tang 1

// topics top 6 topics

large language models 2 ai infrastructure 1 ai research 1 machine learning 1 generative ai 1 artificial intelligence 1