whisper : add integer quantization support (#540)

* whisper : add integer quantization support

* examples : add common-ggml + prepare to add "quantize" tool

* whisper : quantization tool ready

* whisper : fix F32 support

* whisper : try to fix shared lib linkage

* wasm : update quantized models to Q5

* bench.wasm : remove "medium" button

* bench.wasm : fix custom model button

* ggml : add Q5_0 and Q5_1 WASM SIMD

* wasm : add quantized models to all WASM examples

* wasm : bump DB version number to 2

* talk-llama : update example to latest llama.cpp

* node : increase test timeout to 10s

* readme : add information for model quantization

* wasm : add links to other examples
This commit is contained in:
Georgi Gerganov
2023-04-30 18:51:57 +03:00
committed by GitHub
parent 5fd1bdd7fc
commit 794b162a46
41 changed files with 3183 additions and 1010 deletions

View File

@@ -1,16 +1,8 @@
if (WHISPER_SDL2)
# talk
set(TARGET talk)
#add_executable(${TARGET} talk.cpp gpt-2.cpp)
#target_include_directories(${TARGET} PRIVATE ${SDL2_INCLUDE_DIRS})
#target_link_libraries(${TARGET} PRIVATE whisper ${SDL2_LIBRARIES} ${CMAKE_THREAD_LIBS_INIT})
# TODO: this is temporary
# need to export ggml symbols for MSVC, but too lazy ..
add_executable(${TARGET} talk.cpp gpt-2.cpp ../common.cpp ../common-sdl.cpp ../../ggml.c ../../whisper.cpp)
add_executable(${TARGET} talk.cpp gpt-2.cpp)
target_link_libraries(${TARGET} PRIVATE common common-sdl whisper ${CMAKE_THREAD_LIBS_INIT})
include(DefaultTargetOptions)
target_include_directories(${TARGET} PRIVATE ${SDL2_INCLUDE_DIRS} ../../)
target_link_libraries(${TARGET} PRIVATE ${SDL2_LIBRARIES} ${CMAKE_THREAD_LIBS_INIT})
endif ()