News for hackers. Stuff that matters.

A comment on Show HN: Alpaca.cpp – Run an Instruction-Tuned Chat-Style LLM on a MacBook. Parent comment

Re:Show HN: Alpaca.cpp – Run an Instruction-Tuned Chat-Style... by antimatter15 on Thursday March 16, 2023 @02:03PM (#35185756)
It inherits from ARM NEON optimizations in llama.cpp but I believe it should also work on x86.
[ Parent | on HN ]
Re:Show HN: Alpaca.cpp – Run an Instruction-Tuned Chat-Style... by gpderetta on Thursday March 16, 2023 @02:15PM (#35185963)
it built in a couple of seconds with no issues on my x86 machine. Downloading weights now.
[ Parent | on HN ]
Re:Show HN: Alpaca.cpp – Run an Instruction-Tuned Chat-Style... by gorbypark on Thursday March 16, 2023 @03:36PM (#35187180)
Someone contributed AVX2 support a few days after the initial release, so llama.cpp (and the alpaca.cpp fork) should work on most x86 CPUs as well now.
[ Parent | on HN ]
Re:Show HN: Alpaca.cpp – Run an Instruction-Tuned Chat-Style... by inaka10100101 on Thursday March 16, 2023 @04:31PM (#35188067)
Can we run it in colab. It isn't working for me.
[ Parent | on HN ]