mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-21 22:33:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

build: Make target improvements (#7499)

Browse Source 
* llama: wire up builtin runner

This adds a new entrypoint into the ollama CLI to run the cgo built runner.
On Mac arm64, this will have GPU support, but on all other platforms it will
be the lowest common denominator CPU build.  After we fully transition
to the new Go runners more tech-debt can be removed and we can stop building
the "default" runner via make and rely on the builtin always.

* build: Make target improvements

Add a few new targets and help for building locally.
This also adjusts the runner lookup to favor local builds, then
runners relative to the executable, and finally payloads.

* Support customized CPU flags for runners

This implements a simplified custom CPU flags pattern for the runners.
When built without overrides, the runner name contains the vector flag
we check for (AVX) to ensure we don't try to run on unsupported systems
and crash.  If the user builds a customized set, we omit the naming
scheme and don't check for compatibility.  This avoids checking
requirements at runtime, so that logic has been removed as well.  This
can be used to build GPU runners with no vector flags, or CPU/GPU
runners with additional flags (e.g. AVX512) enabled.

* Use relative paths

If the user checks out the repo in a path that contains spaces, make gets
really confused so use relative paths for everything in-repo to avoid breakage.

* Remove payloads from main binary

* install: clean up prior libraries

This removes support for v0.3.6 and older versions (before the tar bundle)
and ensures we clean up prior libraries before extracting the bundle(s).
Without this change, runners and dependent libraries could leak when we
update and lead to subtle runtime errors.
This commit is contained in:
Daniel Hiltgen
2024-12-10 09:47:19 -08:00
committed by GitHub
parent 63269668c0
commit 4879a234c4
58 changed files with 877 additions and 1168 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
llama/llama.go
View File

@@ -9,22 +9,24 @@ package llama
#cgo amd64,avx CXXFLAGS: -mavx
#cgo amd64,avx2 CFLAGS: -mavx2 -mfma
#cgo amd64,avx2 CXXFLAGS: -mavx2 -mfma
#cgo amd64,avx512 CFLAGS: -mavx512f -mavx512dq -mavx512bw
#cgo amd64,avx512 CXXFLAGS: -mavx512f -mavx512dq -mavx512bw
#cgo amd64,avx512bf16 CFLAGS: -mavx512bf16 -D__AVX512BF16__
#cgo amd64,avx512bf16 CXXFLAGS: -mavx512bf16 -D__AVX512BF16__
#cgo amd64,avx512vbmi CFLAGS: -mavx512vbmi -D__AVX512VBMI__
#cgo amd64,avx512vbmi CXXFLAGS: -mavx512vbmi -D__AVX512VBMI__
#cgo amd64,avx512vnni CFLAGS: -mavx512vnni -D__AVX512VNNI__
#cgo amd64,avx512vnni CXXFLAGS: -mavx512vnni -D__AVX512VNNI__
#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_jetpack5 LDFLAGS: -lggml_cuda_jetpack5 -L/usr/local/cuda-11/lib64
#cgo cuda_jetpack6 LDFLAGS: -lggml_cuda_jetpack6 -L/usr/local/cuda-12/lib64
#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 cuda_jetpack5 LDFLAGS: -lggml_cuda_jetpack5
#cgo cuda_jetpack6 LDFLAGS: -lggml_cuda_jetpack6
#cgo cuda_v11 LDFLAGS: -lggml_cuda_v11
#cgo cuda_v12 LDFLAGS: -lggml_cuda_v12
#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
@@ -36,28 +38,24 @@ package llama
#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,amd64 LDFLAGS: -L${SRCDIR}/build/Linux/amd64
#cgo linux,amd64 LDFLAGS: -L${SRCDIR}/build/Linux/amd64
#cgo linux,amd64 LDFLAGS: -L${SRCDIR}/build/linux-amd64
#cgo linux,arm64 CFLAGS: -D__aarch64__ -D__ARM_NEON -D__ARM_FEATURE_FMA
#cgo linux,arm64 CXXFLAGS: -D__aarch64__ -D__ARM_NEON -D__ARM_FEATURE_FMA
#cgo linux,arm64 LDFLAGS: -L${SRCDIR}/build/Linux/arm64
#cgo linux,arm64 LDFLAGS: -L${SRCDIR}/build/linux-arm64
#cgo linux,arm64,sve CFLAGS: -march=armv8.6-a+sve
#cgo linux,arm64,sve CXXFLAGS: -march=armv8.6-a+sve
#cgo linux,cuda LDFLAGS: -lcuda -lcudart -lcublas -lcublasLt -lpthread -ldl -lrt -lresolv
#cgo linux,rocm LDFLAGS: -L/opt/rocm/lib -lpthread -ldl -lrt -lresolv
#cgo linux,rocm LDFLAGS: -lpthread -ldl -lrt -lresolv
#cgo rocm CFLAGS: -DGGML_USE_CUDA -DGGML_USE_HIPBLAS -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_MMV_Y=1 -DGGML_BUILD=1
#cgo rocm CXXFLAGS: -DGGML_USE_CUDA -DGGML_USE_HIPBLAS -DGGML_CUDA_DMMV_X=32 -DGGML_CUDA_PEER_MAX_BATCH_SIZE=128 -DGGML_CUDA_MMV_Y=1 -DGGML_BUILD=1
#cgo rocm LDFLAGS: -L${SRCDIR} -lggml_rocm -lhipblas -lamdhip64 -lrocblas
#cgo windows CFLAGS: -Wno-discarded-qualifiers -D_WIN32_WINNT=0x602
#cgo windows CXXFLAGS: -D_WIN32_WINNT=0x602
#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,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${SRCDIR}/build/Windows/arm64
#cgo windows,arm64 LDFLAGS: -L${SRCDIR}/build/windows-arm64
#cgo windows,cuda LDFLAGS: -lcuda -lcudart -lcublas -lcublasLt
#cgo windows,rocm LDFLAGS: -lggml_rocm -lhipblas -lamdhip64 -lrocblas