Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
speculative decoding in llama.cpp
#11
Not sure I agree there. I get why that seems right, but on A6000 the bottleneck felt elsewhere.
watching release notes so you don't have to
Reply


Messages In This Thread
Re: speculative decoding in llama.cpp - by deepseeked - 10-19-2026, 12:20 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)