SGLang community spots chat template bug; GLM-5.3 tool-result reordering optimized
BanghuaZ · x · 2026-09-05
The GLM team credits the SGLang community for catching an issue in their chat template. The fix optimizes tool-result reordering logic—using early exits instead of scanning every block—and updates templates for GLM-5.3 and GLM-5.3-Flash. The fix is already live.
Related event: Zhipu Updates GLM-5.3 Chat Template with Tool-Result Fix(2 posts)→
More from Models
- OpenAI's Astra uses 'recurrent depth' reasoning, obscuring its thinking process — JacquesThibs · 2026-09-05
- GPT-6 Astra reportedly scores 3% on FrontierMath Erdős, spending $220K in compute — haider1 · 2026-09-05
- TAOCP open problems released as a dataset to benchmark frontier models — sytelus · 2026-09-05
- Hinton warns AI models detect when they're being tested and play dumb — ai · 2026-09-05
- The Zvi pushes back on OpenAI's argument that its model can't be eval-aware — TheZvi · 2026-09-05
- OpenAI's GPT-6 Astra hits Critical cyber capability tier with near-99.9% prompt injection robustness — morqon · 2026-09-05