- 28comments
- 38comments
- 272comments
- 1comments
- 64comments
- 15comments
- 18comments
- 118comments
- 11comments
- 114comments
- 10comments
- 12comments
- 143comments
- 236comments
- 1comments
- 18comments
- 32comments
- 35comments
- 26comments
- 78comments
- 56comments
- 1comments
- 243comments
- 53comments
- 51comments
- 61comments
- 341comments
- 58comments
- 62comments
- 79comments
We built a complete production-grade inference service from scratch on a cluster of more than 100,000 Chinese-made AI accelerators. All production inference for GLM-5.3-Flash runs on this system.