mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-06-26 11:45:21 +00:00
f5cd27b71d
* add common_json w/ support for truncated json healing * add common_chat_msg_diff * partial common_chat_parse * refactor parser w/ optionals * server: wire chat diffs in stream mode * fix trigger of thinking models (must happen after thoughts are closed) * fix functionary v3.2 raw python! * rename: common_chat_syntax (now contains format) * rm common_regex.at_start * don't return empty <think></think> * accommodate yet another deepseek r1 distill fantasy syntax (`<｜tool▁calls｜>`) * fix QwQ 32B tool call parsing after thoughts (hermes2) * better logs for grammar triggers * consume spaces after parse_json_tool_calls * fix required tool calls w/ thinking models that have pre-opened thinking tags * fix thinking model's initial trigger + test qwq's template * run most test_tool_call tests in stream + non-stream modes * make functionary v3.2 parsing more strict (differentiate first match from others) * send final diff from server, to close off raw python arguments * support partial content streaming in Generic mode * tool-call: allow content prelude before hermes2 tool calls (for Qwen2.5) * Update function-calling.md * Update tool_bench.py * chat-parser: remove input from exception (llm output may contain PII) --------- Co-authored-by: ochafik <ochafik@google.com> Co-authored-by: Olivier Chafik <ochafik@users.noreply.github.com>
180 lines
8.2 KiB
CMake
180 lines
8.2 KiB
CMake
llama_add_compile_flags()
|
|
|
|
function(llama_build source)
|
|
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} ${source})
|
|
target_link_libraries(${TEST_TARGET} PRIVATE common)
|
|
install(TARGETS ${TEST_TARGET} RUNTIME)
|
|
endfunction()
|
|
|
|
function(llama_test target)
|
|
include(CMakeParseArguments)
|
|
set(options)
|
|
set(oneValueArgs NAME LABEL WORKING_DIRECTORY)
|
|
set(multiValueArgs ARGS)
|
|
cmake_parse_arguments(LLAMA_TEST "${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 ${LLAMA_TEST_LABEL})
|
|
endfunction()
|
|
|
|
# Builds and runs a test source file.
|
|
# Optional args:
|
|
# - NAME: name of the executable & test target (defaults to the source file name without extension)
|
|
# - LABEL: label for the test (defaults to main)
|
|
# - ARGS: arguments to pass to the test executable
|
|
# - WORKING_DIRECTORY
|
|
function(llama_build_and_test source)
|
|
include(CMakeParseArguments)
|
|
set(options)
|
|
set(oneValueArgs NAME LABEL WORKING_DIRECTORY)
|
|
set(multiValueArgs ARGS)
|
|
cmake_parse_arguments(LLAMA_TEST "${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
|
|
llama_build(test-tokenizer-0.cpp)
|
|
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-bert-bge ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-bert-bge.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-command-r ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-command-r.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-deepseek-llm ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-deepseek-llm.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-gpt-2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-2.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-llama-spm ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-spm.gguf)
|
|
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-phi-3 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-phi-3.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-qwen2.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-refact ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf)
|
|
llama_test(test-tokenizer-0 NAME test-tokenizer-0-starcoder ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-starcoder.gguf)
|
|
|
|
if (LLAMA_LLGUIDANCE)
|
|
llama_build_and_test(test-grammar-llguidance.cpp ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-bpe.gguf)
|
|
endif ()
|
|
|
|
if (NOT WIN32)
|
|
# these tests are disabled on Windows because they use internal functions not exported with LLAMA_API
|
|
llama_build_and_test(test-sampling.cpp)
|
|
llama_build_and_test(test-grammar-parser.cpp)
|
|
llama_build_and_test(test-grammar-integration.cpp)
|
|
llama_build_and_test(test-llama-grammar.cpp)
|
|
llama_build_and_test(test-chat.cpp)
|
|
# TODO: disabled on loongarch64 because the ggml-ci node lacks Python 3.8
|
|
if (NOT ${CMAKE_SYSTEM_PROCESSOR} MATCHES "loongarch64")
|
|
llama_build_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}/../tools/server)
|
|
endif()
|
|
|
|
if (NOT GGML_BACKEND_DL)
|
|
llama_build(test-quantize-stats.cpp)
|
|
endif()
|
|
|
|
llama_build(test-gbnf-validator.cpp)
|
|
|
|
# build test-tokenizer-1-bpe target once and add many tests
|
|
llama_build(test-tokenizer-1-bpe.cpp)
|
|
|
|
# TODO: disabled due to slowness
|
|
#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-falcon ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-falcon.gguf)
|
|
#llama_test(test-tokenizer-1-bpe NAME test-tokenizer-1-gpt-2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-2.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-llama-bpe ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-bpe.gguf --ignore-merges)
|
|
#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-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)
|
|
|
|
# build test-tokenizer-1-spm target once and add many tests
|
|
llama_build(test-tokenizer-1-spm.cpp)
|
|
|
|
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 ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-baichuan.gguf)
|
|
|
|
# llama_build_and_test(test-double-float.cpp) # SLOW
|
|
endif()
|
|
|
|
llama_build_and_test(test-chat-parser.cpp)
|
|
llama_build_and_test(test-chat-template.cpp)
|
|
llama_build_and_test(test-json-partial.cpp)
|
|
llama_build_and_test(test-log.cpp)
|
|
llama_build_and_test(test-regex-partial.cpp)
|
|
|
|
# this fails on windows (github hosted runner) due to curl DLL not found (exit code 0xc0000135)
|
|
if (NOT WIN32)
|
|
llama_build_and_test(test-arg-parser.cpp)
|
|
endif()
|
|
|
|
# llama_build_and_test(test-opt.cpp) # SLOW
|
|
llama_build_and_test(test-gguf.cpp)
|
|
llama_build_and_test(test-backend-ops.cpp)
|
|
|
|
llama_build_and_test(test-model-load-cancel.cpp LABEL "model")
|
|
llama_build_and_test(test-autorelease.cpp LABEL "model")
|
|
|
|
if (NOT GGML_BACKEND_DL)
|
|
# these tests use the backends directly and cannot be built with dynamic loading
|
|
llama_build_and_test(test-barrier.cpp)
|
|
llama_build_and_test(test-quantize-fns.cpp)
|
|
llama_build_and_test(test-quantize-perf.cpp)
|
|
llama_build_and_test(test-rope.cpp)
|
|
endif()
|
|
|
|
# libmtmd
|
|
set(LLAMA_TEST_NAME test-mtmd-c-api)
|
|
llama_build_and_test(test-mtmd-c-api.c)
|
|
target_link_libraries(${LLAMA_TEST_NAME} PRIVATE mtmd)
|
|
|
|
# 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)
|