Vikshy is not being updated. Updates were paused on 20 October 2026, so the news, the Score, prices and rankings here are out of date and will stay as they are. Check the labs' own sites for anything newer.
AmazonResearchMateriality 2

AWS shows bi-directional KV transfer in vLLM cutting TTFT

AWS describes bi-directional KV cache transfer in vLLM that lets prefill and decode nodes reuse computed context across turns. It reports time to first token improvements of up to 1.6x for Qwen3-32B and 3.3x for GLM-5-FP8 on EC2 P5en instances with EFA.

First seen 19 Oct, 16:03 UTC on AWS Machine Learning blog2 sourcesLast update 14h ago

What the sources say

Linked, never rewritten. Official means the lab itself.

How it unfolded

Every source in the order it appeared. Times in UTC.

Keep up with Amazon