6
Serving GLM-5.3 at 607.8 tok/s across two Nvidia DGX stations with vLLM (developer.nvidia.com)
submitted 17 hours ago by [B] to c/hackernews@lemmy.bestiver.se
2 comments fedilink hide all child comments
 

Comments

all 2 comments

sorted by: hot top controversial new old
[–] 4 points 12 hours ago (1 child)

Ah yes, just need to get me two $85k work stations and bridge them together

  • permalink
  • fedilink
  • source
  • hideshow 1 child comment
    •