X · @teortaxesTex
· X / Twitter
As in V4, so here, and now everywhere.
As in V4, so here, and now everywhere.SGLang: Our ecosystem project and the RL framework behind GLM series training, Slime, just open-sourced its deterministic train–rollout alignment path for GLM-5.2. Megatron training and SGLang rollout matched down to a 4096-token logprob MAE of 1.9e-7, with exact zero hidden-state