Skip to content

ggml : move CPU backend to a separate file #10144

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Nov 3, 2024
Merged

ggml : move CPU backend to a separate file #10144

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bf95fff
ggml : move CPU backend to a separate file
slaren Nov 3, 2024
673f95b
restore use of GGML_PRINT_DEBUG in ggml-cpu.c
slaren Nov 3, 2024
0825ba2
revert synchronization change to ggml_init
slaren Nov 3, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 8 additions & 13 deletions Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,6 @@
# Define the default target now so that it is always the first target
BUILD_TARGETS = \
libllava.a \
llama-baby-llama \
llama-batched \
llama-batched-bench \
llama-bench \
Expand Down Expand Up @@ -56,14 +55,14 @@ TEST_TARGETS = \
tests/test-llama-grammar \
tests/test-log \
tests/test-model-load-cancel \
tests/test-opt \
tests/test-quantize-fns \
tests/test-quantize-perf \
tests/test-rope \
tests/test-sampling \
tests/test-tokenizer-0 \
tests/test-tokenizer-1-bpe \
tests/test-tokenizer-1-spm
# tests/test-opt \

# Legacy build targets that were renamed in #7809, but should still be removed when the project is cleaned
LEGACY_TARGETS_CLEAN = main quantize quantize-stats perplexity imatrix embedding vdot q8dot convert-llama2c-to-ggml \
Expand Down Expand Up @@ -916,6 +915,7 @@ endif # GGML_METAL

OBJ_GGML += \
ggml/src/ggml.o \
ggml/src/ggml-cpu.o \
ggml/src/ggml-alloc.o \
ggml/src/ggml-backend.o \
ggml/src/ggml-quants.o \
Expand All @@ -936,7 +936,6 @@ OBJ_COMMON = \
common/console.o \
common/ngram-cache.o \
common/sampling.o \
common/train.o \
common/build-info.o \
common/json-schema-to-grammar.o

Expand Down Expand Up @@ -1048,6 +1047,12 @@ ggml/src/ggml.o: \
ggml/include/ggml.h
$(CC) $(CFLAGS) -c $< -o $@

ggml/src/ggml-cpu.o: \
ggml/src/ggml-cpu.c \
ggml/include/ggml.h \
ggml/src/ggml-common.h
$(CC) $(CFLAGS) -c $< -o $@

ggml/src/ggml-alloc.o: \
ggml/src/ggml-alloc.c \
ggml/include/ggml.h \
Expand Down Expand Up @@ -1213,11 +1218,6 @@ common/json-schema-to-grammar.o: \
common/json-schema-to-grammar.h
$(CXX) $(CXXFLAGS) -c $< -o $@

common/train.o: \
common/train.cpp \
common/train.h
$(CXX) $(CXXFLAGS) -c $< -o $@

common/ngram-cache.o: \
common/ngram-cache.cpp \
common/ngram-cache.h
Expand Down Expand Up @@ -1390,11 +1390,6 @@ llama-bench: examples/llama-bench/llama-bench.cpp \
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)

llama-baby-llama: examples/baby-llama/baby-llama.cpp \
$(OBJ_ALL)
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)

llama-export-lora: examples/export-lora/export-lora.cpp \
$(OBJ_ALL)
$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
Expand Down
1 change: 1 addition & 0 deletions Package.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@ var sources = [
"src/unicode.cpp",
"src/unicode-data.cpp",
"ggml/src/ggml.c",
"ggml/src/ggml-cpu.c",
"ggml/src/ggml-alloc.c",
"ggml/src/ggml-backend.cpp",
"ggml/src/ggml-quants.c",
Expand Down
2 changes: 0 additions & 2 deletions common/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,8 +66,6 @@ add_library(${TARGET} STATIC
ngram-cache.h
sampling.cpp
sampling.h
train.cpp
train.h
)

if (BUILD_SHARED_LIBS)
Expand Down
2 changes: 2 additions & 0 deletions common/common.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1951,6 +1951,8 @@ void yaml_dump_string_multiline(FILE * stream, const char * prop_name, const cha

void yaml_dump_non_result_info(FILE * stream, const common_params & params, const llama_context * lctx,
const std::string & timestamp, const std::vector<int> & prompt_tokens, const char * model_desc) {
ggml_cpu_init(); // some ARM features are detected at runtime
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I didn't get around to it, but this PR reminds me that I also want to at some point remove the YAML log code again. It has become pretty outdated and nowadays there are better solutions for the things that I was originally using it for.


const auto & sparams = params.sparams;

fprintf(stream, "build_commit: %s\n", LLAMA_COMMIT);
Expand Down
Loading
Loading