flâneur

GLM-5.2 RL weight transfer in 4 seconds using NIXL and ModelExpress

primeintellect.ai · 2,758 words · saved by 1 readers

How prime-rl transfers a 1.6 TB GLM-5.2 policy into DPEP=32 vLLM inference, overlaps online quantization, and reduces end-to-end synchronization from 86.1 seconds to 3.9 seconds.

GLM-5.2 RL weight transfer in 4 seconds using NIXL and ModelExpress In RL at 1T Scale, we detailed how prime-rl trains trillion-parameter models like GLM-5 with sub-5-minute step times on just 28 H200 nodes. That speedup exposed a new bottleneck: syncing updated weights from trainer to inference after every step, which stayed stuck at 60-90 seconds no matter how fast everything else got. Here, we rebuild that hand-off on NIXL and ModelExpress, cutting weight transfer for GLM-5.2 down to single-digit seconds and removing the static-process-group constraints that stood in the way of…

saved by

related reading