mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-10 15:57:04 +00:00
4879a234c4
* 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.
197 lines
7.5 KiB
Makefile
197 lines
7.5 KiB
Makefile
# Helpers for managing our vendored llama.cpp repo and patch set
|
|
|
|
REPO_ROOT:=./
|
|
DEST_DIR:=./llama/
|
|
|
|
include $(DEST_DIR)vendoring
|
|
|
|
LLAMACPP_REPO := ./llama/vendor/
|
|
|
|
# Relative to the vendor dir
|
|
VENDOR_RELATIVE_PATCH_DIR := ../patches/
|
|
|
|
|
|
help-sync:
|
|
@echo "The following make targets will help you update llama.cpp to a new base commit, or work on new features/fixes"
|
|
@echo ""
|
|
@echo " make apply-patches # Establish the tracking repo if not already present, reset to the base commit, and apply our patch set"
|
|
@echo " make sync # Vendor llama.cpp and ggml from the tracking repo working tree"
|
|
@echo " make sync-clean # Remove all vendored files"
|
|
@echo " make create-patches # Generate the patch set based on the current commits in the tracking repo since the base commit"
|
|
@echo ""
|
|
@echo "For more details on the workflow, see the Vendoring section in 'docs/development.md'"
|
|
|
|
apply-patches: $(LLAMACPP_REPO)
|
|
@if ! git -C $(LLAMACPP_REPO) --no-pager diff --exit-code ; then \
|
|
echo "ERROR: Your llama.cpp repo is dirty. The apply-patches target requires a clean working tree"; \
|
|
echo "To clobber: git -C $(LLAMACPP_REPO) reset --hard HEAD" ; \
|
|
exit 1; \
|
|
fi
|
|
@echo "Checking out $(LLAMACPP_BASE_COMMIT)"
|
|
@git -C $(LLAMACPP_REPO) checkout -q $(LLAMACPP_BASE_COMMIT) || \
|
|
git -C $(LLAMACPP_REPO) fetch --all && git -C $(LLAMACPP_REPO) checkout -q $(LLAMACPP_BASE_COMMIT)
|
|
@echo "Applying ollama patches..."
|
|
@cd $(LLAMACPP_REPO) && git -c 'user.name=nobody' -c 'user.email=<>' am -3 $(VENDOR_RELATIVE_PATCH_DIR)*.patch || \
|
|
echo "Please resolve the conflicts in $(LLAMACPP_REPO), and run 'git am --continue' to continue applying subsequent patches"
|
|
@echo ""
|
|
@echo "The tracking repo $(LLAMACPP_REPO) is now in a detached state with all patches applied."
|
|
@echo "Don't forget to commit any changes you make and run 'make create-patches' "
|
|
|
|
$(LLAMACPP_REPO):
|
|
@echo "Cloning llama.cpp to $(LLAMACPP_REPO)"
|
|
git clone https://github.com/ggerganov/llama.cpp.git $@
|
|
|
|
create-patches: $(LLAMACPP_REPO)
|
|
@if ! git -C $(LLAMACPP_REPO) --no-pager diff --exit-code ; then \
|
|
echo "ERROR: Your llama.cpp repo is dirty. You must commit any pending changes for format-patch to generate patches"; \
|
|
exit 1; \
|
|
fi
|
|
@cd $(LLAMACPP_REPO) && git format-patch --no-signature --no-numbered --zero-commit -o $(VENDOR_RELATIVE_PATCH_DIR) $(LLAMACPP_BASE_COMMIT)
|
|
|
|
# Vendoring template logic
|
|
EXCLUDED_FILES=sgemm.cpp sgemm.h sampling_ext.cpp sampling_ext.h stb_image.h json.hpp llama_darwin.c base64.hpp
|
|
OLLAMA_NATIVE_FILES=mllama.cpp mllama.h llama_darwin.c sampling_ext.cpp sampling_ext.h
|
|
define vendor_file
|
|
$(strip $(addprefix $(2),$(notdir $1))) : $(addprefix $(LLAMACPP_REPO),$(1))
|
|
ifneq ($$(filter-out $(EXCLUDED_FILES),$(notdir $1)),)
|
|
@echo "vendoring $1"; \
|
|
mkdir -p $$(dir $$@) && \
|
|
echo "/**" > $$@ && \
|
|
echo " * llama.cpp - commit $$(LLAMACPP_BASE_COMMIT) - do not edit this file" >> $$@ && \
|
|
echo " *" >> $$@ && \
|
|
sed 's/^/ * /' <$(LLAMACPP_REPO)/LICENSE | sed 's/ *$$$$//' >> $$@ && \
|
|
echo " */" >> $$@ && \
|
|
echo "" >> $$@ && \
|
|
cat $$< >> $$@
|
|
else
|
|
@echo "vendoring $1"; \
|
|
mkdir -p $$(dir $$@) && \
|
|
cat $$< > $$@
|
|
endif
|
|
VENDORED_FILES += $(strip $(addprefix $(2),$(notdir $1)))
|
|
endef
|
|
|
|
# llama.cpp files -> llama/
|
|
LLAMACPP_FILES=\
|
|
src/unicode.cpp \
|
|
src/unicode.h \
|
|
src/unicode-data.cpp \
|
|
src/unicode-data.h \
|
|
src/llama.cpp \
|
|
src/llama-impl.h \
|
|
src/llama-vocab.cpp \
|
|
src/llama-vocab.h \
|
|
src/llama-grammar.cpp \
|
|
src/llama-grammar.h \
|
|
src/llama-sampling.cpp \
|
|
src/llama-sampling.h \
|
|
include/llama.h \
|
|
ggml/src/llamafile/sgemm.cpp \
|
|
ggml/src/llamafile/sgemm.h
|
|
$(foreach name,$(LLAMACPP_FILES),$(eval $(call vendor_file,$(name),$(DEST_DIR))))
|
|
|
|
# llama.cpp files -> llama/llamafile
|
|
LLAMAFILE_FILES= \
|
|
ggml/src/llamafile/sgemm.h
|
|
$(foreach name,$(LLAMAFILE_FILES),$(eval $(call vendor_file,$(name),$(DEST_DIR)llamafile/)))
|
|
|
|
# ggml files -> llama/
|
|
GGML_FILES= \
|
|
ggml/src/ggml.c \
|
|
ggml/include/ggml.h \
|
|
ggml/src/ggml-quants.c \
|
|
ggml/src/ggml-quants.h \
|
|
ggml/src/ggml-metal.metal \
|
|
ggml/include/ggml-metal.h \
|
|
ggml/src/ggml-impl.h \
|
|
ggml/include/ggml-cuda.h \
|
|
ggml/src/ggml-cuda.cu \
|
|
ggml/src/ggml-common.h \
|
|
ggml/include/ggml-backend.h \
|
|
ggml/src/ggml-backend.c \
|
|
ggml/src/ggml-backend-impl.h \
|
|
ggml/include/ggml-alloc.h \
|
|
ggml/src/ggml-alloc.c \
|
|
ggml/src/ggml-aarch64.h \
|
|
ggml/src/ggml-aarch64.c \
|
|
ggml/src/ggml-cpu-impl.h \
|
|
ggml/include/ggml-blas.h \
|
|
ggml/src/ggml-blas.cpp
|
|
$(foreach name,$(GGML_FILES),$(eval $(call vendor_file,$(name),$(DEST_DIR))))
|
|
|
|
# TODO generalize renaming pattern if we have more of these
|
|
$(DEST_DIR)ggml-metal_darwin_arm64.m : $(LLAMACPP_REPO)ggml/src/ggml-metal.m
|
|
@echo "vendoring $(subst $(LLAMACPP_REPO),,$<)"; \
|
|
mkdir -p $(dir $@) && \
|
|
echo "/**" > $@ && \
|
|
echo " * llama.cpp - commit $(LLAMACPP_BASE_COMMIT) - do not edit this file" >> $@ && \
|
|
echo " *" >> $@ && \
|
|
sed 's/^/ * /' <$(LLAMACPP_REPO)/LICENSE | sed 's/ *$$//' >> $@ && \
|
|
echo " */" >> $@ && \
|
|
echo "" >> $@ && \
|
|
cat $< >> $@
|
|
VENDORED_FILES += $(DEST_DIR)ggml-metal_darwin_arm64.m
|
|
|
|
# ggml-cuda -> llama/ggml-cuda/
|
|
GGML_CUDA_FILES= ggml/src/ggml-cuda/*.cu ggml/src/ggml-cuda/*.cuh
|
|
GGML_CUDA_FILES_EXPANDED = $(addprefix ggml/src/ggml-cuda/,$(notdir $(wildcard $(addprefix $(LLAMACPP_REPO),$(GGML_CUDA_FILES)))))
|
|
$(foreach name,$(GGML_CUDA_FILES_EXPANDED),$(eval $(call vendor_file,$(name),$(DEST_DIR)ggml-cuda/)))
|
|
|
|
GGML_TEMPLATE_FILES= ggml/src/ggml-cuda/template-instances/*.cu
|
|
GGML_TEMPLATE_FILES_EXPANDED = $(addprefix ggml/src/ggml-cuda/template-instances/,$(notdir $(wildcard $(addprefix $(LLAMACPP_REPO),$(GGML_TEMPLATE_FILES)))))
|
|
$(foreach name,$(GGML_TEMPLATE_FILES_EXPANDED),$(eval $(call vendor_file,$(name),$(DEST_DIR)ggml-cuda/template-instances/)))
|
|
|
|
GGML_VENDOR_FILES= ggml/src/ggml-cuda/vendors/*.h
|
|
GGML_VENDOR_FILES_EXPANDED=$(addprefix ggml/src/ggml-cuda/vendors/,$(notdir $(wildcard $(addprefix $(LLAMACPP_REPO),$(GGML_VENDOR_FILES)))))
|
|
$(foreach name,$(GGML_VENDOR_FILES_EXPANDED),$(eval $(call vendor_file,$(name),$(DEST_DIR)ggml-cuda/vendors/)))
|
|
|
|
# llava -> llama/
|
|
LAVA_FILES= \
|
|
examples/llava/clip.cpp \
|
|
examples/llava/clip.h \
|
|
examples/llava/llava.cpp \
|
|
examples/llava/llava.h \
|
|
common/log.h \
|
|
common/log.cpp \
|
|
common/stb_image.h
|
|
# These files are mostly used by the llava code
|
|
# and shouldn't be necessary once we use clip.cpp directly
|
|
LAVA_FILES+= \
|
|
common/common.cpp \
|
|
common/common.h \
|
|
common/sampling.cpp \
|
|
common/sampling.h \
|
|
common/json.hpp \
|
|
common/json-schema-to-grammar.cpp \
|
|
common/json-schema-to-grammar.h \
|
|
common/base64.hpp
|
|
$(foreach name,$(LAVA_FILES),$(eval $(call vendor_file,$(name),$(DEST_DIR))))
|
|
|
|
$(DEST_DIR)build-info.cpp:
|
|
@echo "Generating $@"
|
|
@echo "int LLAMA_BUILD_NUMBER = 0;" > $@
|
|
@echo "char const *LLAMA_COMMIT = \"$(LLAMACPP_BASE_COMMIT)\";" >> $@
|
|
@echo "char const *LLAMA_COMPILER = \"\";" >> $@
|
|
@echo "char const *LLAMA_BUILD_TARGET = \"\";" >> $@
|
|
VENDORED_FILES += $(DEST_DIR)build-info.cpp
|
|
|
|
|
|
sync: $(LLAMACPP_REPO) .WAIT $(VENDORED_FILES) .WAIT remove-stale-files
|
|
|
|
sync-clean:
|
|
rm -f $(VENDORED_FILES) $(EXTRA_NATIVE_FILES)
|
|
|
|
PATS=*.c *.h *.cpp *.m *.metal *.cu *.cuh
|
|
NATIVE_DIRS=$(DEST_DIR) $(DEST_DIR)llamafile/ $(DEST_DIR)ggml-cuda/ $(DEST_DIR)ggml-cuda/template-instances/ $(DEST_DIR)ggml-cuda/vendors/
|
|
ALL_NATIVE_FILES=$(foreach dir,$(NATIVE_DIRS),$(wildcard $(addprefix $(dir),$(PATS))))
|
|
EXTRA_NATIVE_FILES=$(filter-out $(VENDORED_FILES) $(addprefix $(DEST_DIR),$(OLLAMA_NATIVE_FILES)), $(ALL_NATIVE_FILES))
|
|
remove-stale-files:
|
|
@rm -f $(EXTRA_NATIVE_FILES)
|
|
|
|
.PHONY: help-sync apply-patches sync create-patches remove-stale-fails .WAIT
|
|
|
|
|
|
# Handy debugging for make variables
|
|
print-%:
|
|
@echo '$*=$($*)'
|