Inference › Training & Customization › Dataset Creation / Curation
embedding model you trust on 7900 XTX

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Threaded Mode
embedding model you trust on 7900 XTX
torchkite Offline
Junior Member
**
Posts: 33
Threads: 0
Joined: Aug 2026
Reputation: 0
#11
10-18-2026, 04:02 PM
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not quality.
Find
Reply
batchsize Offline
Member
***
Posts: 137
Threads: 16
Joined: Sep 2026
Reputation: 0
#12
10-19-2026, 02:05 AM
Quote:I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly. The main thing that moved was latency, not qual

I'd start with the simpler stack.
throughput matters, but tail latency matters too
Find
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)