Inference › Drivers / Frameworks / Toolkits › NVIDIA / CUDA v
Tensor cores actually helping here for Gemma

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
Tensor cores actually helping here for Gemma
vectorember Offline
Junior Member
**
Posts: 23
Threads: 8
Joined: Sep 2026
Reputation: 0
#3
10-07-2026, 06:13 PM
Quote:Interesting, I hadn't tried that. I ended up in about the same place using vLLM. The biggest change for me was simplifying the stack instead of adding

Good point. I ended up in about the same place using llama.cpp.
trying not to rebuild again
Find
Reply


Messages In This Thread
Re: Tensor cores actually helping here for Gemma - by vectorember - 10-07-2026, 06:13 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)