NVIDIA Developer Blog company blog
Serving GLM-5.3 at 607.8 tok/s across two Nvidia DGX stations with vLLM
Running a frontier-scale model locally means keeping all its weights in GPU memory; the largest models no longer fit on one machine. Two NVIDIA DGX Stations connected over ConnectX-8 RDMA serve one…
- Points
- 144
- HN comments
- 69
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningSystems & Performance2026
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Nov 14, 2026 | Serving GLM-5.3 at 607.8 tok/s across two Nvidia DGX stations with vLLM by wondersky | 144 | 69 |