Understand this story
Hao AI Lab discloses a stall issue in SGLang's PD-disaggregated decode servers: a single aborted request freezes the transfer queue, while the /health check still returns 200. The team observed with vstack on GB200 that the decode server stalled for 364.69 seconds, during which all 363 health checks passed. Hao AI Lab states that gating only new preallocations is enough to let already-arrived transfers complete and resolve the stall. This issue is one of 20+ issues and fix PRs the team proposed in collaboration with the SGLang community.
AI-generated from public reports
Latest development · Report
Hao AI Lab uses vstack to discover SGLang decode server hang of 364 secondsDevelopments
1 confirmed developments
- Source:UCSD Hao AI Lab
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 18
UCSD Hao AI LabFirst-party
Hao AI Lab uses vstack to discover SGLang decode server hang of 364 seconds
Hao AI Lab used vstack to discover a PD-disaggregated decode server hang issue in SGLang: a single aborted request freezes the transfer queue, while /health still returns 200. On GB200, the decode server stalled for 364.69 seconds, and all 363 health checks passed; gating only new preallocations allows already-arrived transfers to complete and resolves the hang. This issue is one of 20+ issues and fix PRs proposed in collaboration with the SGLang community.
AI Trends