Llama.cpp: Full CUDA GPU Acceleration

Re:Llama.cpp: Full CUDA GPU Acceleration by cshimmin on Tuesday June 13, 2023 @12:30AM (#36305334)

So, the solution is that everyone should write code as self-contained C++ code and not use any software libraries ever. Dependency hell has been solved for all time!

[ Parent | on HN ]

Re:Llama.cpp: Full CUDA GPU Acceleration by sp332 on Tuesday June 13, 2023 @12:48AM (#36305480)

Well, in the cases where the libraries are causing more work than they are solving. Then yes.

[ Parent | on HN ]

Re:Llama.cpp: Full CUDA GPU Acceleration by Tostino on Tuesday June 13, 2023 @12:58AM (#36305580)

There is a happy medium... somewhere. After following Postgres development for the better part of a decade, I think it's definitely closer to the python side of things... But man they (python) do make it hard to like using that ecosystem.

The flip side is like you said... You will just have to reimplement everything yourself and then you can never worry about dependencies again! Just hope you didn't introduce some obscure security issue in your hashmap implementation .

[ Parent | on HN ]

Re:Llama.cpp: Full CUDA GPU Acceleration by josephg on Tuesday June 13, 2023 @01:13AM (#36305714)

Python was released in 1991. It obviously didn’t get package management right, just like C and C++ didn’t figure it out in the 70s.

Take a look at rust’s Cargo for what a modern package manager should look like. Or deno / Go if you swing that way.

Which old language gets package management right? None of them. None of them get it right.

And sure - conda / venv / CMake / etc help. But last century’s bad design decisions still shine through.

[ Parent | on HN ]