Inference › Drivers / Frameworks / Toolkits › NVIDIA / CUDA v
batching changes after update with llama.cpp

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
batching changes after update with llama.cpp
audioriver Offline
Member
***
Posts: 69
Threads: 3
Joined: Sep 2026
Reputation: 0
#3
10-02-2026, 06:14 AM
Interesting, I hadn't tried that. I ended up in about the same place using TensorRT-LLM. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
still benchmarking everything
Find
Reply


Messages In This Thread
Re: batching changes after update with llama.cpp - by audioriver - 10-02-2026, 06:14 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)