Inference › Drivers / Frameworks / Toolkits › AMD / ROCm v
ROCm version that finally behaves: early impressions

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
ROCm version that finally behaves: early impressions
cozywire Offline
Junior Member
**
Posts: 37
Threads: 4
Joined: Sep 2026
Reputation: 0
#1
10-01-2026, 02:34 PM
Did a bit of testing and thought I'd post the result here.

Short version: llama.cpp behaved well for me, but only after I stopped ignoring batch size.

Happy to post more details if anyone wants them.
Find
Reply


Messages In This Thread
ROCm version that finally behaves: early impressions - by cozywire - 10-01-2026, 02:34 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)