Serving GLM-5.3-Flash on one Trainium2 box with NKI layer megakernels (runanywhere.ai via hn) glm 11d
event
Inference Server Update
-
One AWS trn2.48xlarge serves GLM-5.3-Flash at up to 28.9 agent requests a minute on SemiAnalysis's AgentX benchmark, 3.57 million tokens a minute, and takes a million-token prompt to its first token in about three minutes. NKI layer megake…
-
Show HN: A live-built agent newsroom for tracking midterms today (midterms2026.noriagentic.com via hn) glmsonnet 12d
We set up a bunch of agents to act as a live newsroom for the midterms. There are 6 regional desks tracking parts of the US (mostly sonnet and sol), 2 political partisans (glm 5.3 so they wont get blocked by guardrails), a newsroom head, a…