Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
latest release actually worth attention on 5090
#1
Spent some time on this today and wanted to compare notes.

Two paths both seem viable, but they break down differently once KV cache pressure becomes important.

Interested in tradeoffs more than fan loyalty.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

The part that surprised me was how much the boring details mattered more than the model choice.
Reply
#2
Thanks, that helps. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Reply
#3
Good point. I ended up in about the same place using vLLM.
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)