Merge branch 'main' into fix/windows-cuda-dll-build
This commit is contained in:
mohamedmastouri2000-boop
+97
-25
@@ -14,7 +14,7 @@ TRIPLET := $(shell $(DETECT_CC) -dumpmachine 2>/dev/null)
|
||||
MINGW := $(findstring mingw,$(TRIPLET))
|
||||
CYGWIN := $(findstring cygwin,$(TRIPLET))
|
||||
DARWIN := $(findstring darwin,$(TRIPLET))
|
||||
PPC64 := $(findstring powerpc64,$(TRIPLET))
|
||||
LINUX := $(findstring linux,$(TRIPLET))
|
||||
IS_WIN := $(MINGW)$(CYGWIN)
|
||||
|
||||
# Fallbacks for the rare toolchain that does not answer -dumpmachine: keep the
|
||||
@@ -26,10 +26,17 @@ ifeq ($(IS_WIN),)
|
||||
UNAME_S := $(shell uname -s)
|
||||
UNAME_M := $(shell uname -m)
|
||||
DARWIN := $(findstring Darwin,$(UNAME_S))
|
||||
PPC64 := $(findstring ppc64,$(UNAME_M))
|
||||
endif
|
||||
endif
|
||||
|
||||
TARGET_CPU := $(firstword $(subst -, ,$(TRIPLET)))
|
||||
ifeq ($(TARGET_CPU),)
|
||||
TARGET_CPU := $(UNAME_M)
|
||||
endif
|
||||
X86_64 := $(filter x86_64 amd64,$(TARGET_CPU))
|
||||
AARCH64 := $(filter aarch64 arm64,$(TARGET_CPU))
|
||||
PPC64 := $(filter powerpc64% ppc64%,$(TARGET_CPU))
|
||||
|
||||
ifneq (,$(DARWIN))
|
||||
# --- macOS / Apple Silicon ---
|
||||
# Apple clang non include il runtime OpenMP: se c'e' libomp di Homebrew lo usa
|
||||
@@ -37,7 +44,9 @@ ifneq (,$(DARWIN))
|
||||
# Niente -march: su arm64 NEON e' baseline (i kernel __ARM_NEON si attivano da soli).
|
||||
CC = clang
|
||||
OMPDIR := $(shell brew --prefix libomp 2>/dev/null)
|
||||
ifneq ($(OMPDIR),)
|
||||
# `brew --prefix libomp` can print the formula's prospective path even when it
|
||||
# is not installed, so verify both artifacts before adding unusable flags.
|
||||
ifneq ($(and $(OMPDIR),$(wildcard $(OMPDIR)/include/omp.h),$(wildcard $(OMPDIR)/lib/libomp.*)),)
|
||||
OMPC = -Xclang -fopenmp -I$(OMPDIR)/include
|
||||
OMPL = -L$(OMPDIR)/lib -lomp
|
||||
else
|
||||
@@ -46,6 +55,12 @@ OMPC =
|
||||
OMPL =
|
||||
endif
|
||||
CFLAGS = -O3 $(OMPC) -Wall -Wextra -Wno-unused-parameter -Wno-misleading-indentation -Wno-unused-function
|
||||
# Opt-in: ARCH=native appends -mcpu=native (arm64 clang uses -mcpu, not -march),
|
||||
# which unlocks the i8mm SMMLA int8/int4 dot kernels in glm.c. ARCH unset ->
|
||||
# no -mcpu, default build byte-identical. Apple clang knows apple-m4 / native.
|
||||
ifneq ($(ARCH),)
|
||||
CFLAGS += -mcpu=$(ARCH)
|
||||
endif
|
||||
LDFLAGS = -lm $(OMPL)
|
||||
EXE =
|
||||
else ifneq ($(IS_WIN),)
|
||||
@@ -60,7 +75,11 @@ else ifneq ($(IS_WIN),)
|
||||
CC = gcc
|
||||
ARCH ?= x86-64-v3
|
||||
CFLAGS = -D_FILE_OFFSET_BITS=64 -O3 -march=$(ARCH) -fopenmp -Wall -Wextra -Wno-unused-parameter -Wno-misleading-indentation -Wno-unused-function
|
||||
LDFLAGS = -lm -fopenmp -static
|
||||
# -lpsapi: compat.h calls GetProcessMemoryInfo (rss_gb). It's linked via
|
||||
# #pragma comment(lib,"psapi.lib") for MSVC, but MinGW gcc ignores that pragma
|
||||
# (warns), so link psapi explicitly or the build fails undefined-reference on
|
||||
# modern GCC (e.g. 16.x under UCRT). Harmless where the pragma also resolves it.
|
||||
LDFLAGS = -lm -fopenmp -static -lpsapi
|
||||
EXE = .exe
|
||||
else
|
||||
ifneq (,$(PPC64))
|
||||
@@ -70,18 +89,19 @@ ifneq (,$(PPC64))
|
||||
# (validated token-exact vs the transformers oracle on a POWER8 S824).
|
||||
CC = gcc
|
||||
ARCH ?= native
|
||||
CFLAGS = -O3 -mcpu=$(ARCH) -fopenmp -Wall -Wextra -Wno-unused-parameter -Wno-misleading-indentation -Wno-unused-function
|
||||
LDFLAGS = -lm -fopenmp
|
||||
CFLAGS = -O3 -mcpu=$(ARCH) -fopenmp -pthread -Wall -Wextra -Wno-unused-parameter -Wno-misleading-indentation -Wno-unused-function
|
||||
LDFLAGS = -lm -fopenmp -pthread
|
||||
EXE =
|
||||
else
|
||||
# --- Linux x86-64 (percorso originale, invariato) ---
|
||||
# --- Linux / *BSD x86-64 (percorso originale, invariato) ---
|
||||
CC = gcc
|
||||
# ARCH=native -> ottimizzato per QUESTA macchina (default, piu' veloce).
|
||||
# ARCH=x86-64-v3 -> binario PORTABILE su qualsiasi x86-64 moderno con AVX2 (per distribuire).
|
||||
# ARCH=x86-64 -> massima compatibilita' (niente AVX2: usa il path scalare di fallback).
|
||||
# -pthread: Linux lo tira dentro via -fopenmp, i *BSD no e le pthread_* non risolvono (#219).
|
||||
ARCH ?= native
|
||||
CFLAGS = -O3 -march=$(ARCH) -fopenmp -Wall -Wextra -Wno-unused-parameter -Wno-misleading-indentation -Wno-unused-function
|
||||
LDFLAGS = -lm -fopenmp
|
||||
CFLAGS = -O3 -march=$(ARCH) -fopenmp -pthread -Wall -Wextra -Wno-unused-parameter -Wno-misleading-indentation -Wno-unused-function
|
||||
LDFLAGS = -lm -fopenmp -pthread
|
||||
EXE =
|
||||
endif
|
||||
endif
|
||||
@@ -105,22 +125,51 @@ INSTALL ?= install
|
||||
# clean. See backend_loader.c and README "cuda-dll" below.
|
||||
CUDA ?= 0
|
||||
CUDA_DLL ?= 0
|
||||
ifneq ($(IS_WIN),)
|
||||
# the CUDA installer sets CUDA_PATH system-wide (e.g. C:\Program Files\NVIDIA
|
||||
# GPU Computing Toolkit\CUDA\v13.2); fall back to it before the POSIX default.
|
||||
# NVCC defaults to plain `nvcc` from PATH: CUDA_PATH contains spaces, which the
|
||||
# unquoted recipe checks cannot survive — and the cuda-dll recipe already
|
||||
# requires an MSVC environment (vcvars64) on PATH, so requiring the CUDA bin
|
||||
# directory too is symmetric. The installer adds it by default.
|
||||
CUDA_HOME ?= $(subst \,/,$(CUDA_PATH))
|
||||
NVCC ?= nvcc
|
||||
# Host compiler override for nvcc (e.g. Fedora ships g++16 but CUDA needs 15):
|
||||
# make glm CUDA=1 NVCC_CCBIN=g++-15 (opt-in: unset = nvcc's own default)
|
||||
ifneq ($(NVCC_CCBIN),)
|
||||
NVCCFLAGS += -ccbin $(NVCC_CCBIN)
|
||||
endif
|
||||
else
|
||||
CUDA_HOME ?= /usr/local/cuda
|
||||
NVCC ?= $(CUDA_HOME)/bin/nvcc
|
||||
endif
|
||||
CUDA_ARCH ?= native
|
||||
# -Xcompiler passes flags to nvcc's HOST compiler. On Windows that host is MSVC
|
||||
# cl.exe, which rejects the gcc/clang-style -Wall,-Wextra (D8021). Gate them
|
||||
# behind a non-MSVC host so the Linux/macOS (gcc/clang) build keeps the warnings
|
||||
# and the Windows cuda-dll build doesn't fail. (#306)
|
||||
NVCC_HOST_WARN ?= $(if $(IS_WIN),,-Xcompiler=-Wall,-Wextra)
|
||||
NVCCFLAGS ?= -O3 -std=c++17 -arch=$(CUDA_ARCH) $(NVCC_HOST_WARN)
|
||||
ifeq ($(IS_WIN),)
|
||||
PYTHON ?= python3
|
||||
ifneq ($(IS_WIN),)
|
||||
# nvcc's host compiler on Windows is MSVC cl.exe: the GCC-style
|
||||
# -Xcompiler=-Wall,-Wextra is rejected ("D8021 invalid numeric argument
|
||||
# '/Wextra'"), which made `make cuda-dll` unbuildable as shipped. -W3 is
|
||||
# the MSVC warning level (dash form, NOT /W3: MSYS make would mangle the
|
||||
# slash-form into a filesystem path).
|
||||
NVCCFLAGS ?= -O3 -std=c++17 -arch=$(CUDA_ARCH) -Xcompiler=-W3
|
||||
else
|
||||
NVCCFLAGS ?= -O3 -std=c++17 -arch=$(CUDA_ARCH) -Xcompiler=-Wall,-Wextra
|
||||
endif
|
||||
# PYTHON is a HOST tool (clean/test-c/test-python run it on the build machine),
|
||||
# so key it off the host, NOT $(IS_WIN) — which is derived from the *target*
|
||||
# triple ($(CC) -dumpmachine). Otherwise a cross build (make CC=x86_64-w64-
|
||||
# mingw32-gcc ... on Linux) sets IS_WIN and picks `python`, breaking clean/test
|
||||
# on hosts where only `python3` exists. $(OS)=Windows_NT in every Windows shell
|
||||
# (the #129 signal) and is empty on Linux/macOS.
|
||||
ifeq ($(OS),Windows_NT)
|
||||
PYTHON ?= python
|
||||
else
|
||||
PYTHON ?= python3
|
||||
endif
|
||||
CUDA_OBJ =
|
||||
TEST_BINS = tests/test_json$(EXE) tests/test_st$(EXE) tests/test_tier$(EXE) tests/test_grammar$(EXE) tests/test_decode_batch$(EXE) tests/test_idot$(EXE) tests/test_i4_acc512$(EXE) tests/test_compat_direct$(EXE)
|
||||
TEST_BINS = tests/test_json$(EXE) tests/test_st$(EXE) tests/test_tier$(EXE) tests/test_grammar$(EXE) tests/test_schema_gbnf$(EXE) tests/test_decode_batch$(EXE) tests/test_idot$(EXE) tests/test_kv_alloc$(EXE) tests/test_i4_acc512$(EXE) tests/test_compat_direct$(EXE)
|
||||
ifneq (,$(LINUX))
|
||||
TEST_BINS += tests/test_uring$(EXE)
|
||||
endif
|
||||
|
||||
# Windows CUDA DLL path: host links the loader, NOT cudart.
|
||||
ifneq ($(IS_WIN),)
|
||||
@@ -148,7 +197,7 @@ endif
|
||||
# runtime, so no Xcode / offline metal compiler is required. Default build unchanged.
|
||||
METAL ?= 0
|
||||
METAL_OBJ =
|
||||
METALXX = clang++ -x objective-c++ -fobjc-arc -O3
|
||||
METALXX = clang++ -x objective-c++ -std=gnu++17 -fobjc-arc -O3
|
||||
ifeq ($(METAL),1)
|
||||
ifeq (,$(DARWIN))
|
||||
$(error METAL=1 is supported only on macOS)
|
||||
@@ -177,7 +226,7 @@ $(shell printf '%s' '$(BUILD_CONFIG)' > .build-config)
|
||||
endif
|
||||
.build-config: ;
|
||||
|
||||
glm$(EXE): glm.c st.h json.h tok.h tok_unicode.h compat.h grammar.h $(CUDA_OBJ) $(METAL_OBJ) .build-config
|
||||
glm$(EXE): glm.c st.h uring.h json.h tok.h tok_unicode.h compat.h grammar.h $(CUDA_OBJ) $(METAL_OBJ) .build-config
|
||||
$(CC) $(CFLAGS) glm.c $(CUDA_OBJ) $(METAL_OBJ) -o glm$(EXE) $(LDFLAGS)
|
||||
|
||||
# Windows runtime loader object: resolves coli_cuda_* from coli_cuda.dll.
|
||||
@@ -188,7 +237,7 @@ backend_loader.o: backend_loader.c backend_cuda.h compat.h .build-config
|
||||
# compiler, required by nvcc on Windows) into coli_cuda.dll. Run this from a
|
||||
# shell that has the MSVC environment set (e.g. after vcvars64.bat, or from a
|
||||
# "x64 Native Tools Command Prompt"). COLI_CUDA_BUILDING_DLL enables
|
||||
# __declspec(dllexport) so the 11 API symbols are exported.
|
||||
# __declspec(dllexport) so the 15 API symbols are exported.
|
||||
cuda-dll: backend_cuda.cu backend_cuda.h
|
||||
@command -v "$(NVCC)" >/dev/null 2>&1 || { echo "nvcc not found: set CUDA_HOME or NVCC" >&2; exit 1; }
|
||||
@command -v cl >/dev/null 2>&1 || { echo "cl.exe (MSVC) not in PATH — run vcvars64.bat first" >&2; exit 1; }
|
||||
@@ -220,9 +269,23 @@ cuda-bench: backend_cuda.cu backend_cuda.h tests/bench_tensor_core.cu
|
||||
olmoe$(EXE): olmoe.c st.h json.h compat.h
|
||||
$(CC) $(CFLAGS) olmoe.c -o olmoe$(EXE) $(LDFLAGS)
|
||||
|
||||
# binario portabile da distribuire su altre macchine x86-64
|
||||
# Use a baseline that matches the compiler target. macOS already targets a
|
||||
# portable baseline when ARCH is empty; forcing the x86 value there breaks
|
||||
# Apple Silicon. Unknown targets use native rather than an invalid x86 flag.
|
||||
ifneq (,$(DARWIN))
|
||||
PORTABLE_ARCH =
|
||||
else ifneq (,$(AARCH64))
|
||||
PORTABLE_ARCH = armv8-a
|
||||
else ifneq (,$(PPC64))
|
||||
PORTABLE_ARCH = power8
|
||||
else ifneq (,$(X86_64))
|
||||
PORTABLE_ARCH = x86-64-v3
|
||||
else
|
||||
PORTABLE_ARCH = native
|
||||
endif
|
||||
|
||||
portable:
|
||||
$(MAKE) glm$(EXE) ARCH=x86-64-v3
|
||||
$(MAKE) glm$(EXE) ARCH=$(PORTABLE_ARCH)
|
||||
|
||||
iobench$(EXE): iobench.c compat.h
|
||||
$(CC) $(CFLAGS) iobench.c -o iobench$(EXE) $(LDFLAGS)
|
||||
@@ -239,10 +302,16 @@ tests/test_tier$(EXE): tests/test_tier.c tier.h
|
||||
tests/test_grammar$(EXE): tests/test_grammar.c grammar.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test_schema_gbnf$(EXE): tests/test_schema_gbnf.c schema_gbnf.h grammar.h json.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test_decode_batch$(EXE): tests/test_decode_batch.c decode_batch.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test_idot$(EXE): tests/test_idot.c glm.c st.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h
|
||||
tests/test_idot$(EXE): tests/test_idot.c glm.c st.h uring.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test_kv_alloc$(EXE): tests/test_kv_alloc.c glm.c st.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test_i4_acc512$(EXE): tests/test_i4_acc512.c
|
||||
@@ -251,6 +320,9 @@ tests/test_i4_acc512$(EXE): tests/test_i4_acc512.c
|
||||
tests/test_compat_direct$(EXE): tests/test_compat_direct.c compat.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test_uring$(EXE): tests/test_uring.c glm.c st.h uring.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
test-c: $(TEST_BINS)
|
||||
$(PYTHON) tools/run_tests.py $(TEST_BINS)
|
||||
|
||||
@@ -284,4 +356,4 @@ clean:
|
||||
|
||||
bench: iobench$(EXE)
|
||||
@if [ -n "$(ARGS)" ]; then ./iobench$(EXE) $(ARGS); else echo "built iobench$(EXE) — run: ./iobench$(EXE) <file> <MB> <iters> <threads> <direct 0|1>"; fi
|
||||
.PHONY: all glm cuda-test cuda-bench cuda-dll portable test-c test-python test check clean install uninstall bench
|
||||
.PHONY: all glm cuda-test cuda-bench cuda-dll portable test-c test-python test check clean install uninstall bench
|
||||
|
||||
Reference in New Issue
Block a user