vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

OpenCL Token Generation Acceleration (#1459)

Browse source 
* Move back to C++ for OpenCL

* Refactor OpenCL code to work more like the CUDA code, add missing functions

* Deduplicate dequant kernels

* Add OpenCL compile options

* Use compile args for preprocessing constants

* Restore default platform + device selection by id behavior

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
Co-authored-by: Henri Vasserman <henv@hot.ee>
This commit is contained in:
0cc4m 2023-05-22 23:33:24 +02:00 • committed by GitHub
parent 7e4ea5beff
commit 2e6cd4b025
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 1113 additions and 536 deletions
Download patch file Download diff file Expand all files Collapse all files

5
Makefile
View file

@ -138,6 +138,7 @@ ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
endif
ifdef LLAMA_CLBLAST
CFLAGS += -DGGML_USE_CLBLAST
CXXFLAGS += -DGGML_USE_CLBLAST
# Mac provides OpenCL as a framework
ifeq ($(UNAME_S),Darwin)
LDFLAGS += -lclblast -framework OpenCL
@ -145,8 +146,8 @@ ifdef LLAMA_CLBLAST
LDFLAGS += -lclblast -lOpenCL
endif
OBJS += ggml-opencl.o
ggml-opencl.o: ggml-opencl.c ggml-opencl.h
$(CC) $(CFLAGS) -c $< -o $@
ggml-opencl.o: ggml-opencl.cpp ggml-opencl.h
$(CXX) $(CXXFLAGS) -c $< -o $@
endif
ifneq ($(filter aarch64%,$(UNAME_M)),)
# Apple M1, M2, etc.