Llama.cpp: Full CUDA GPU Acceleration

Re:Llama.cpp: Full CUDA GPU Acceleration by bhy on Tuesday June 13, 2023 @03:20AM (#36306739)

Well I just spent an hour to diagnose the build failure of llama.cpp due to it picking up wrong nvcc path.

Dependency problem still happens even with C/C++.

[ Parent | on HN ]

Re:Llama.cpp: Full CUDA GPU Acceleration by Tostino on Tuesday June 13, 2023 @03:28AM (#36306791)

I had the same issue... Turned out it was because I used the flat pack version of intellij idea and it had problems with paths. Running from a plain terminal worked fine.

[ Parent | on HN ]

Re:Llama.cpp: Full CUDA GPU Acceleration by Faceless1230 on Tuesday June 13, 2023 @07:45AM (#36308786)

The flatpak version of intellij isn't officially maintained by jetbrains. Jetbrains only maintains the snap for linux

[ Parent | on HN ]

Re:Llama.cpp: Full CUDA GPU Acceleration by paulmd on Tuesday June 13, 2023 @11:49AM (#36312034)

it's fortunate that flatpak solves this problem of reproducible environments so effectively

[ Parent | on HN ]