mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-06-26 19:55:04 +00:00
ggml : add CLBlast support (#1164)
* Allow use of OpenCL GPU-based BLAS using ClBlast instead of OpenBLAS for context processing * Improve ClBlast implementation, avoid recreating buffers, remove redundant transfers * Finish merge of ClBlast support * Move CLBlast implementation to separate file Add buffer reuse code (adapted from slaren's cuda implementation) * Add q4_2 and q4_3 CLBlast support, improve code * Double CLBlast speed by disabling OpenBLAS thread workaround Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com> Co-authored-by: slaren <2141330+slaren@users.noreply.github.com> * Fix device selection env variable names * Fix cast in opencl kernels * Add CLBlast to CMakeLists.txt * Replace buffer pool with static buffers a, b, qb, c Fix compile warnings * Fix typos, use GGML_TYPE defines, improve code * Improve btype dequant kernel selection code, add error if type is unsupported * Improve code quality * Move internal stuff out of header * Use internal enums instead of CLBlast enums * Remove leftover C++ includes and defines * Make event use easier to read Co-authored-by: Henri Vasserman <henv@hot.ee> * Use c compiler for opencl files * Simplify code, fix include * First check error, then release event * Make globals static, fix indentation * Rename dequant kernels file to conform with other file names * Fix import cl file name --------- Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com> Co-authored-by: slaren <2141330+slaren@users.noreply.github.com> Co-authored-by: Henri Vasserman <henv@hot.ee> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
@ -67,6 +67,7 @@ endif()
|
||||
option(LLAMA_ACCELERATE "llama: enable Accelerate framework" ON)
|
||||
option(LLAMA_OPENBLAS "llama: use OpenBLAS" OFF)
|
||||
option(LLAMA_CUBLAS "llama: use cuBLAS" OFF)
|
||||
option(LLAMA_CLBLAST "llama: use CLBlast" OFF)
|
||||
|
||||
option(LLAMA_BUILD_TESTS "llama: build tests" ${LLAMA_STANDALONE})
|
||||
option(LLAMA_BUILD_EXAMPLES "llama: build examples" ${LLAMA_STANDALONE})
|
||||
@ -168,6 +169,21 @@ if (LLAMA_CUBLAS)
|
||||
endif()
|
||||
endif()
|
||||
|
||||
if (LLAMA_CLBLAST)
|
||||
find_package(CLBlast)
|
||||
if (CLBlast_FOUND)
|
||||
message(STATUS "CLBlast found")
|
||||
|
||||
set(GGML_OPENCL_SOURCES ggml-opencl.c ggml-opencl.h)
|
||||
|
||||
add_compile_definitions(GGML_USE_CLBLAST)
|
||||
|
||||
set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} clblast)
|
||||
else()
|
||||
message(WARNING "CLBlast not found")
|
||||
endif()
|
||||
endif()
|
||||
|
||||
if (LLAMA_ALL_WARNINGS)
|
||||
if (NOT MSVC)
|
||||
set(c_flags
|
||||
@ -307,7 +323,8 @@ endif()
|
||||
add_library(ggml OBJECT
|
||||
ggml.c
|
||||
ggml.h
|
||||
${GGML_CUDA_SOURCES})
|
||||
${GGML_CUDA_SOURCES}
|
||||
${GGML_OPENCL_SOURCES})
|
||||
|
||||
target_include_directories(ggml PUBLIC .)
|
||||
target_compile_features(ggml PUBLIC c_std_11) # don't bump
|
||||
|
Reference in New Issue
Block a user