llama.cpp/tests/CMakeLists.txt
Georgi Gerganov 92139b90af
tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)
* tests : add test-tokenizer-0.sh

* unicode : add all unicode number ranges

* starcoder : fix pre-tokenizer

* tests : add test that fails with DeepSeek tokenizers

* falcon : fix regex

* unicode : regenerate unicode tables

* refact : add tokenizer model

* lint : fix

* tests : disable failing tests

ggml-ci

* refact : add tests files

ggml-ci

* convert : print -> logging

ggml-ci

* lint : fix

* unicode : digit -> number

* phi-3 : update
2024-05-04 08:32:32 +03:00

137 lines
7.0 KiB
CMake

function(llama_test target)
include(CMakeParseArguments)
set(options)
set(oneValueArgs NAME LABEL WORKING_DIRECTORY)
set(multiValueArgs ARGS)
cmake_parse_arguments(LLAMA_TEST "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
if (NOT DEFINED LLAMA_TEST_LABEL)
set(LLAMA_TEST_LABEL "main")
endif()
if (NOT DEFINED LLAMA_TEST_WORKING_DIRECTORY)
set(LLAMA_TEST_WORKING_DIRECTORY .)
endif()
if (DEFINED LLAMA_TEST_NAME)
set(TEST_NAME ${LLAMA_TEST_NAME})
else()
set(TEST_NAME ${target})
endif()
set(TEST_TARGET ${target})
add_test(
NAME ${TEST_NAME}
WORKING_DIRECTORY ${LLAMA_TEST_WORKING_DIRECTORY}
COMMAND $<TARGET_FILE:${TEST_TARGET}>
${LLAMA_TEST_ARGS})
set_property(TEST ${TEST_NAME} PROPERTY LABELS ${LLAMA_TEST_LABEL})
endfunction()
# Builds and runs a test source file.
# Optional args:
# - NAME: name of the executable & test target (defaults to the source file name without extension)
# - LABEL: label for the test (defaults to main)
# - ARGS: arguments to pass to the test executable
# - WORKING_DIRECTORY
function(llama_target_and_test source)
include(CMakeParseArguments)
set(options)
set(oneValueArgs NAME LABEL WORKING_DIRECTORY)
set(multiValueArgs ARGS)
cmake_parse_arguments(LLAMA_TEST "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
if (NOT DEFINED LLAMA_TEST_LABEL)
set(LLAMA_TEST_LABEL "main")
endif()
if (NOT DEFINED LLAMA_TEST_WORKING_DIRECTORY)
set(LLAMA_TEST_WORKING_DIRECTORY .)
endif()
if (DEFINED LLAMA_TEST_NAME)
set(TEST_TARGET ${LLAMA_TEST_NAME})
else()
get_filename_component(TEST_TARGET ${source} NAME_WE)
endif()
add_executable(${TEST_TARGET} ${source} get-model.cpp)
install(TARGETS ${TEST_TARGET} RUNTIME)
target_link_libraries(${TEST_TARGET} PRIVATE common)
add_test(
NAME ${TEST_TARGET}
WORKING_DIRECTORY ${LLAMA_TEST_WORKING_DIRECTORY}
COMMAND $<TARGET_FILE:${TEST_TARGET}>
${LLAMA_TEST_ARGS})
set_property(TEST ${TEST_TARGET} PROPERTY LABELS ${LLAMA_TEST_LABEL})
endfunction()
# build test-tokenizer-0 target once and add many tests
add_executable(test-tokenizer-0 test-tokenizer-0.cpp)
target_link_libraries(test-tokenizer-0 PRIVATE common)
install(TARGETS test-tokenizer-0 RUNTIME)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-spm ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-spm.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-bpe ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-bpe.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-phi-3 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-phi-3.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-falcon ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-falcon.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-bert-bge ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-bert-bge.gguf)
# TODO: enable when fixed
# https://github.com/ggerganov/llama.cpp/pull/7036
#llama_test(test-tokenizer-0 NAME test-tokenizer-0-mpt ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-mpt.gguf)
#llama_test(test-tokenizer-0 NAME test-tokenizer-0-deepseek-llm ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-deepseek-llm.gguf)
#llama_test(test-tokenizer-0 NAME test-tokenizer-0-deepseek-coder ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-deepseek-coder.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-starcoder ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-starcoder.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-gpt-2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-2.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-refact ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf)
# build test-tokenizer-1-bpe target once and add many tests
add_executable(test-tokenizer-1-bpe test-tokenizer-1-bpe.cpp)
target_link_libraries(test-tokenizer-1-bpe PRIVATE common)
install(TARGETS test-tokenizer-1-bpe RUNTIME)
# TODO: disabled due to slowness
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-llama-bpe ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-bpe.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-falcon ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-falcon.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-aquila ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-aquila.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-mpt ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-mpt.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-stablelm ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-stablelm.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-gpt-neox ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-neox.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-refact ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-starcoder ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-starcoder.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-gpt2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt2.gguf)
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-bloom ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-bloom.gguf)
# build test-tokenizer-1-spm target once and add many tests
add_executable(test-tokenizer-1-spm test-tokenizer-1-spm.cpp)
target_link_libraries(test-tokenizer-1-spm PRIVATE common)
install(TARGETS test-tokenizer-1-spm RUNTIME)
llama_test(test-tokenizer-1-spm NAME test-tokenizer-1-llama-spm ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-spm.gguf)
#llama_test(test-tokenizer-1-spm NAME test-tokenizer-1-baichuan ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-baichuan.gguf)
# llama_target_and_test(test-double-float.cpp) # SLOW
llama_target_and_test(test-quantize-fns.cpp)
llama_target_and_test(test-quantize-perf.cpp)
llama_target_and_test(test-sampling.cpp)
llama_target_and_test(test-chat-template.cpp)
llama_target_and_test(test-grammar-parser.cpp)
llama_target_and_test(test-llama-grammar.cpp)
llama_target_and_test(test-grammar-integration.cpp)
llama_target_and_test(test-grad0.cpp)
# llama_target_and_test(test-opt.cpp) # SLOW
llama_target_and_test(test-backend-ops.cpp)
llama_target_and_test(test-rope.cpp)
llama_target_and_test(test-model-load-cancel.cpp LABEL "model")
llama_target_and_test(test-autorelease.cpp LABEL "model")
llama_target_and_test(test-json-schema-to-grammar.cpp WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/..)
target_include_directories(test-json-schema-to-grammar PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/../examples/server)
# dummy executable - not installed
get_filename_component(TEST_TARGET test-c.c NAME_WE)
add_executable(${TEST_TARGET} test-c.c)
target_link_libraries(${TEST_TARGET} PRIVATE llama)