public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-21 01:31:53 +02:00
Code Issues Packages Projects Releases Wiki Activity

whisper : Metal and ggml-alloc support (#1270)

Browse Source 
* metal : init

* whisper : factor out graph builds

* whisper : allocate encoder and decoder using ggml-alloc

* whisper : ggml-alloc is now supported

* whisper : CoreML support ggml-alloc

* build : fix ggml-alloc

* ios : update submodule

* extra : update sync-ggml.sh script to also sync ggml-alloc

* ci : see if this is causing the crash

* whisper : refactor ggml-alloc init

* whisper.android : try to fix build

* whisper : initial Metal version

* ci : try to debug vmem issue

* metal : decoder works on GPU!

* metal : add multi-decoder support

* ggml : fix ggml_nbytes (probably temp solution)

* metal : run "cross" step on the GPU

* whisper : remove ggml_repeat in the encoder

* whisper : offload the Encoder to Metal

* ggml : use simpler ggml_bytes() implementation

* ggml-alloc : try to make CI happy by reducing vram to 128GB

* whisper : add whisper_allocr to wrap ggml_allocr

* whisper : factor out alloc init in a function

* cmake : update to support Metal build

* whisper : add <functional> header

* objc : fix build (no Metal yet)

* ios : add Metal support

* swiftui : fix build

* metal : speed-up KQ multiplication

* metal : sync latest llama.cpp kernels

* readme : add Metal info

* ios : update submodule

* coreml : add code to toggle Core ML config (CPU, ANE, GPU)

* bench : fix timings by running a pre-heat

* bench : start benching the decoder

* whisper : add ggml_mul_mat_pad

* bench : fix uninitialized vars

* whisper : add comment for disabling mul-mat padding

* whisper : add description of ggml_mul_mat_pad

* whisper : clean-up ggml_mul_mat_pad

* metal : remove the "concurrent" flag

* bench : variable n_past

* ios : update SPM package
This commit is contained in:
Georgi Gerganov
2023-09-15 12:18:18 +03:00
committed by GitHub
parent 3fec2119e6
commit 93935980f8
18 changed files with 1855 additions and 1252 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Makefile
+22 -1
View File
@@ -18,7 +18,7 @@ ifndef NVCC_VERSION
endif
endif
CCV := $(shell $(CC) --version | head -n 1)
CCV := $(shell $(CC) --version | head -n 1)
CXXV := $(shell $(CXX) --version | head -n 1)
# Mac OS + Arm can report x86_64
@@ -182,6 +182,15 @@ ifdef WHISPER_COREML_ALLOW_FALLBACK
endif
endif
ifndef WHISPER_NO_METAL
ifeq ($(UNAME_S),Darwin)
WHISPER_METAL := 1
CXXFLAGS += -DGGML_USE_METAL
LDFLAGS += -framework Foundation -framework Metal -framework MetalKit
endif
endif
ifdef WHISPER_OPENBLAS
CFLAGS += -DGGML_USE_OPENBLAS -I/usr/local/include/openblas -I/usr/include/openblas
LDFLAGS += -lopenblas
@@ -288,6 +297,11 @@ $(info )
ggml.o: ggml.c ggml.h ggml-cuda.h
$(CC) $(CFLAGS) -c $< -o $@
ggml-alloc.o: ggml-alloc.c ggml.h ggml-alloc.h
$(CC) $(CFLAGS) -c $< -o $@
WHISPER_OBJ += ggml-alloc.o
whisper.o: whisper.cpp whisper.h ggml.h ggml-cuda.h
$(CXX) $(CXXFLAGS) -c $< -o $@
@@ -303,6 +317,13 @@ whisper-encoder-impl.o: coreml/whisper-encoder-impl.m coreml/whisper-encoder-imp
WHISPER_OBJ += whisper.o whisper-encoder.o whisper-encoder-impl.o
endif
ifdef WHISPER_METAL
ggml-metal.o: ggml-metal.m ggml-metal.h
$(CC) $(CFLAGS) -c $< -o $@
WHISPER_OBJ += ggml-metal.o
endif
libwhisper.a: ggml.o $(WHISPER_OBJ)
$(AR) rcs libwhisper.a ggml.o $(WHISPER_OBJ)