Junchen Jiang

mentions 2 type Person feed RSS

// recent coverage 2 mentions

05:52

2026-08-18

aiunderstanding.org

artificial-intelligence

Paper Says Agent-Aware Cache Management Cuts First-Token Delay Up to 45% in Multi-Agent Serving

A preprint on arXiv (2608.14624) describes CacheScout, a runtime layer for multi-agent language model servers built on vLLM, that learns agent execution transitions to guide cache eviction and prefetc…

22:34

2026-05-28

letsdatascience.com

ai-startups

Tensormesh Raises $20M for KV-Caching Inference Platform

Tensormesh announced $20 million in seed extension funding led by AMD Ventures, with participation from CoreWeave, NVentures, Valley Capital Partners, and Laude Ventures, bringing total capital raised…

// co-occurs with top 8 entities

Tensormesh 1 AMD Ventures 1 CoreWeave 1 NVentures 1 Valley Capital Partners 1 Laude Ventures 1 LMCache 1 CacheScout 1

// topics top 6 topics

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