Inference › Drivers / Frameworks / Toolkits › NVIDIA / CUDA v
Tensor cores actually helping here on dual 3090

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Threaded Mode
Tensor cores actually helping here on dual 3090
audioriver Offline
Member
***
Posts: 69
Threads: 3
Joined: Sep 2026
Reputation: 0
#11
10-10-2026, 04:08 PM
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.
still benchmarking everything
Find
Reply
tinycontext Offline
Member
***
Posts: 112
Threads: 12
Joined: Sep 2026
Reputation: 0
#12
10-10-2026, 04:42 PM
Quote:Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter mor

Ran a quick check on my box. On A6000 with PyTorch, I saw basically the same behavior. The main thing that moved was latency, not quality.
context windows are not a product strategy
Find
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)