llama.cpp
Make CMake LLAMA_NATIVE flag actually use the instructions supported by the processor
#3273

Merged

Make CMake LLAMA_NATIVE flag actually use the instructions supported by the processor #3273

ggerganov merged 10 commits into ggml-org:master from llama_native

fix LLAMA_NATIVE

c0583b2a

syntax

ce6f1a09

Green-Sky approved these changes on 2023-09-20

cebtenzzre commented on 2023-09-20

alternate implementation

169c6228

my eyes must be getting bad...

1310dbed

Merge branch 'ggerganov:master' into llama_native

89cecedf

set cmake LLAMA_NATIVE=ON by default

45916f90

Merge https://github.com/ggerganov/llama.cpp into llama_native

062561d4

march=native doesn't work for ios/tvos, so disable for those targets.…

82832374

cebtenzzre marked this pull request as draft 2 years ago

revert 8283237 and only allow LLAMA_NATIVE on x86 like the Makefile

2c177a46

netrunnereve marked this pull request as ready for review 2 years ago

Green-Sky requested changes on 2023-09-30

remove -DLLAMA_MPI=ON

bc70f21c

Green-Sky approved these changes on 2023-10-01

ggerganov merged 017efe89 into master 2 years ago

netrunnereve deleted the llama_native branch 2 years ago

Reviewers

Green-Sky

cebtenzzre

staviq

Assignees

No one assigned

Labels

None yet

Milestone

No milestone