mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-11 18:36:41 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

llama: add compiler tags for cpu features (#7137)

Browse source 
This adds the ability to customize the default runner with user specified flags
This commit is contained in:
Daniel Hiltgen 2024-10-17 13:43:20 -07:00 • committed by GitHub
parent f2890a4494
commit f86d00cd95
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 52 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

63
llama/llama.go
View file

@ -3,38 +3,59 @@ package llama
/*
#cgo CFLAGS: -O2 -std=c11 -DGGML_BUILD=1 -DNDEBUG -DLOG_DISABLE_LOGS -DGGML_USE_LLAMAFILE
#cgo CXXFLAGS: -O2 -std=c++11 -DGGML_BUILD=1 -DNDEBUG -DLOG_DISABLE_LOGS -DGGML_USE_LLAMAFILE
#cgo darwin,arm64 CFLAGS: -DGGML_USE_METAL -DGGML_USE_ACCELERATE -DGGML_METAL_EMBED_LIBRARY -DACCELERATE_NEW_LAPACK -DACCELERATE_LAPACK_ILP64 -DGGML_USE_BLAS
#cgo darwin,arm64 CXXFLAGS: -DGGML_USE_METAL -DGGML_USE_ACCELERATE -DGGML_METAL_EMBED_LIBRARY -DACCELERATE_NEW_LAPACK -DACCELERATE_LAPACK_ILP64 -DGGML_USE_BLAS
#cgo darwin,arm64 LDFLAGS: -framework Foundation -framework Metal -framework MetalKit -framework Accelerate
#cgo amd64,avx CFLAGS: -mavx
#cgo amd64,avx CXXFLAGS: -mavx
#cgo amd64,avx2 CFLAGS: -mavx2 -mfma
#cgo amd64,avx2 CXXFLAGS: -mavx2 -mfma
#cgo amd64,f16c CFLAGS: -mf16c
#cgo amd64,f16c CXXFLAGS: -mf16c
#cgo amd64,fma CFLAGS: -mfma
#cgo amd64,fma CXXFLAGS: -mfma
#cgo avx CFLAGS: -mavx
#cgo avx CXXFLAGS: -mavx
#cgo avx2 CFLAGS: -mavx2 -mfma -mf16c
#cgo avx2 CXXFLAGS: -mavx2 -mfma -mf16c
#cgo cuda CFLAGS: -fPIE -DGGML_USE_CUDA -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_MMV_Y=1 -DGGML_BUILD=1
#cgo cuda CFLAGS: -fPIE -DGGML_USE_CUDA -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_MMV_Y=1 -DGGML_BUILD=1
#cgo cuda CXXFLAGS: -DGGML_USE_CUDA -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_MMV_Y=1 -DGGML_BUILD=1
#cgo cuda CXXFLAGS: -DGGML_USE_CUDA -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_MMV_Y=1 -DGGML_BUILD=1
#cgo cuda_v11 LDFLAGS: -lggml_cuda_v11 -L/usr/local/cuda-11/lib64
#cgo cuda_v12 LDFLAGS: -lggml_cuda_v12 -L/usr/local/cuda-12/lib64
#cgo darwin,amd64 CFLAGS: -Wno-incompatible-pointer-types-discards-qualifiers
#cgo darwin,amd64 CXXFLAGS: -Wno-incompatible-pointer-types-discards-qualifiers
#cgo darwin,amd64 LDFLAGS: -framework Foundation
#cgo darwin,amd64,avx2 CFLAGS: -DGGML_USE_ACCELERATE -DACCELERATE_NEW_LAPACK -DACCELERATE_LAPACK_ILP64
#cgo darwin,amd64,avx2 CXXFLAGS: -DGGML_USE_ACCELERATE -DACCELERATE_NEW_LAPACK -DACCELERATE_LAPACK_ILP64
#cgo darwin,amd64,avx2 LDFLAGS: -framework Accelerate
#cgo darwin,arm64 CFLAGS: -DGGML_USE_METAL -DGGML_USE_ACCELERATE -DGGML_METAL_EMBED_LIBRARY -DACCELERATE_NEW_LAPACK -DACCELERATE_LAPACK_ILP64 -DGGML_USE_BLAS
#cgo darwin,arm64 CXXFLAGS: -DGGML_USE_METAL -DGGML_USE_ACCELERATE -DGGML_METAL_EMBED_LIBRARY -DACCELERATE_NEW_LAPACK -DACCELERATE_LAPACK_ILP64 -DGGML_USE_BLAS
#cgo darwin,arm64 LDFLAGS: -framework Foundation -framework Metal -framework MetalKit -framework Accelerate
#cgo linux CFLAGS: -D_GNU_SOURCE
#cgo linux CXXFLAGS: -D_GNU_SOURCE
#cgo linux,arm64 LDFLAGS: -L${SRCDIR}/build/Linux/arm64
#cgo linux,amd64 LDFLAGS: -L${SRCDIR}/build/Linux/amd64
#cgo windows CFLAGS: -Wno-discarded-qualifiers
#cgo windows LDFLAGS: -lmsvcrt -static-libstdc++ -static-libgcc -static
#cgo windows,arm64 LDFLAGS: -L${SRCDIR}/build/Windows/arm64
#cgo windows,amd64 LDFLAGS: -L${SRCDIR}/build/Windows/amd64
#cgo avx CFLAGS: -mavx
#cgo avx CXXFLAGS: -mavx
#cgo avx2 CFLAGS: -mavx2 -mfma -mf16c
#cgo avx2 CXXFLAGS: -mavx2 -mfma -mf16c
#cgo cuda CFLAGS: -fPIE -DGGML_USE_CUDA -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_MMV_Y=1
#cgo cuda CXXFLAGS: -fPIE -DGGML_USE_CUDA -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_MMV_Y=1
#cgo rocm CFLAGS: -DGGML_USE_CUDA -DGGML_USE_HIPBLAS -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_MMV_Y=1 -D__HIP_PLATFORM_AMD__=1 -D__HIP_ROCclr__=1
#cgo rocm CXXFLAGS: -DGGML_USE_CUDA -DGGML_USE_HIPBLAS -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_MMV_Y=1 -D__HIP_PLATFORM_AMD__=1 -D__HIP_ROCclr__=1
#cgo rocm LDFLAGS: -L${SRCDIR} -lggml_rocm -lhipblas -lamdhip64 -lrocblas
#cgo cuda_v11 LDFLAGS: -lggml_cuda_v11 -L/usr/local/cuda-11/lib64
#cgo cuda_v12 LDFLAGS: -lggml_cuda_v12 -L/usr/local/cuda-12/lib64
#cgo windows,cuda LDFLAGS: -lcuda -lcudart -lcublas -lcublasLt
#cgo windows,rocm LDFLAGS: -lggml_rocm -lhipblas -lamdhip64 -lrocblas
#cgo linux,amd64 LDFLAGS: -L${SRCDIR}/build/Linux/amd64
#cgo linux,arm64 CFLAGS: -D__aarch64__ -D__ARM_NEON -D__ARM_FEATURE_FMA -D__ARM_FEATURE_MATMUL_INT8
#cgo linux,arm64 CXXFLAGS: -D__aarch64__ -D__ARM_NEON -D__ARM_FEATURE_FMA -D__ARM_FEATURE_MATMUL_INT8
#cgo linux,arm64 LDFLAGS: -L${SRCDIR}/build/Linux/arm64
#cgo linux,arm64,sve CFLAGS: -march=armv8.6-a+sve
#cgo linux,arm64,sve CXXFLAGS: -march=armv8.6-a+sve
#cgo linux,cuda LDFLAGS: -lcuda -lcudart -lcublas -lcublasLt -lpthread -ldl -lrt -lresolv
#cgo linux,rocm LDFLAGS: -L/opt/rocm/lib -lpthread -ldl -lrt -lresolv
#cgo rocm CFLAGS: -DGGML_USE_CUDA -DGGML_USE_HIPBLAS -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_MMV_Y=1 -DGGML_BUILD=1
#cgo rocm CXXFLAGS: -DGGML_USE_CUDA -DGGML_USE_HIPBLAS -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_MMV_Y=1 -DGGML_BUILD=1
#cgo rocm LDFLAGS: -L${SRCDIR} -lggml_rocm -lhipblas -lamdhip64 -lrocblas
#cgo windows CFLAGS: -Wno-discarded-qualifiers
#cgo windows CFLAGS: -Wno-discarded-qualifiers
#cgo windows LDFLAGS: -lmsvcrt
#cgo windows LDFLAGS: -lmsvcrt -static-libstdc++ -static-libgcc -static
#cgo windows,amd64 LDFLAGS: -L${SRCDIR}/build/Windows/amd64
#cgo windows,amd64 LDFLAGS: -L${SRCDIR}/build/Windows/amd64
#cgo windows,arm64 CFLAGS: -D__aarch64__ -D__ARM_NEON -D__ARM_FEATURE_FMA
#cgo windows,arm64 CXXFLAGS: -D__aarch64__ -D__ARM_NEON -D__ARM_FEATURE_FMA
#cgo windows,arm64 LDFLAGS: -L${SRCDIR}/build/Windows/arm64
#cgo windows,arm64 LDFLAGS: -L${SRCDIR}/build/Windows/arm64
#cgo windows,cuda LDFLAGS: -lcuda -lcudart -lcublas -lcublasLt
#cgo windows,rocm LDFLAGS: -lggml_rocm -lhipblas -lamdhip64 -lrocblas
#include <stdlib.h>
#include "llama.h"