dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-06-12 22:04:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 13

chore: detect and enable avx512 builds (#4675)

Browse source 
chore(avx512): add support

Fixes https://github.com/mudler/LocalAI/issues/4662

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-01-24 08:26:44 +01:00 • committed by GitHub
parent f9e368b7c4
commit 5177837ab0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 17 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

8
Makefile
View file

@ -186,6 +186,7 @@ endif
ALL_GRPC_BACKENDS=backend-assets/grpc/huggingface
ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-cpp-avx
ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-cpp-avx2
ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-cpp-avx512
ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-cpp-fallback
ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-ggml
ALL_GRPC_BACKENDS+=backend-assets/grpc/llama-cpp-grpc
@ -699,6 +700,13 @@ backend-assets/grpc/llama-cpp-avx2: backend-assets/grpc backend/cpp/llama/llama.
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on" $(MAKE) VARIANT="llama-avx2" build-llama-cpp-grpc-server
cp -rfv backend/cpp/llama-avx2/grpc-server backend-assets/grpc/llama-cpp-avx2
backend-assets/grpc/llama-cpp-avx512: backend-assets/grpc backend/cpp/llama/llama.cpp
cp -rf backend/cpp/llama backend/cpp/llama-avx512
$(MAKE) -C backend/cpp/llama-avx512 purge
$(info ${GREEN}I llama-cpp build info:avx512${RESET})
CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=on -DGGML_FMA=on -DGGML_F16C=on" $(MAKE) VARIANT="llama-avx512" build-llama-cpp-grpc-server
cp -rfv backend/cpp/llama-avx512/grpc-server backend-assets/grpc/llama-cpp-avx512
backend-assets/grpc/llama-cpp-avx: backend-assets/grpc backend/cpp/llama/llama.cpp
cp -rf backend/cpp/llama backend/cpp/llama-avx
$(MAKE) -C backend/cpp/llama-avx purge