News for hackers. Stuff that matters.

A comment on Llama.cpp 30B runs with only 6GB of RAM now. Parent comment

Re:Llama.cpp 30B runs with only 6GB of RAM now by remexre on Saturday April 01, 2023 @07:19PM (#35405209)
What's c++xx?
[ Parent | on HN ]
Re:Llama.cpp 30B runs with only 6GB of RAM now by opless on Sunday April 02, 2023 @02:06AM (#35407666)
C++11, and greater.
[ Parent | on HN ]
Re:Llama.cpp 30B runs with only 6GB of RAM now by remexre on Sunday April 02, 2023 @07:26PM (#35416499)
Huh, I was proficient in Rust before "properly" learning C++, so maybe that accounts for it, but I didn't realize C++11 was controversial. Is it just move semantics, or are there some library things that are hard to implement?
[ Parent | on HN ]
Re:Llama.cpp 30B runs with only 6GB of RAM now by int_19h on Monday April 03, 2023 @05:30PM (#35431561)
I think what OP is saying is that decades-old systems wouldn't have C++11-compatible compilers on them.
[ Parent | on HN ]
Re:Llama.cpp 30B runs with only 6GB of RAM now by bboygravity on Tuesday April 04, 2023 @11:49AM (#35441542)
And maybe that "C++" is now basically a bunch of different incompatible languages instead of just 1 language, depending on what "xx" is (11, 14, 17, 20, 23, etc).

It's like Python 2 vs Python 3 except even worse.

[ Parent | on HN ]
Re:Llama.cpp 30B runs with only 6GB of RAM now by int_19h on Tuesday April 04, 2023 @02:32PM (#35444029)
In my experience, C++03 code works just fine without changes on a C++11 and C++14 compilers, so no, it's not at all like Python 2/3. The few features that were ripped out were exactly the stuff that pretty much no-one was using for good reasons (e.g. throw-specifications).
[ Parent | on HN ]