llama.cpp/tests/CMakeLists.txt
Olivier Chafik 5b7b0ac8df
json-schema-to-grammar improvements (+ added to server) (#5978)
* json: fix arrays (disallow `[,1]`)

* json: support tuple types (`[number, string]`)

* json: support additionalProperties (`{[k: string]: [string,number][]}`)

* json: support required / optional properties

* json: add support for pattern

* json: resolve $ref (and support https schema urls)

* json: fix $ref resolution

* join: support union types (mostly for nullable types I think)

* json: support allOf + nested anyOf

* json: support any (`{}` or `{type: object}`)

* json: fix merge

* json: temp fix for escapes

* json: spaces in output and unrestricted output spaces

* json: add typings

* json:fix typo

* Create ts-type-to-grammar.sh

* json: fix _format_literal (json.dumps already escapes quotes)

* json: merge lit sequences and handle negatives

{"type": "string", "pattern": "^({\"question\": \"[^\"]+\", \"response\": \"[^\"]+\"}\\n)+$"}

* json: handle pattern repetitions

* Update json-schema-to-grammar.mjs

* Create regex-to-grammar.py

* json: extract repeated regexp patterns to subrule

* Update json-schema-to-grammar.py

* Update json-schema-to-grammar.py

* Update json-schema-to-grammar.py

* json: handle schema from pydantic Optional fields

* Update json-schema-to-grammar.py

* Update json-schema-to-grammar.py

* Update ts-type-to-grammar.sh

* Update ts-type-to-grammar.sh

* json: simplify nullable fields handling

* json: accept duplicate identical rules

* json: revert space to 1 at most

* json: reuse regexp pattern subrules

* json: handle uuid string format

* json: fix literal escapes

* json: add --allow-fetch

* json: simplify range escapes

* json: support negative ranges in patterns

* Delete commit.txt

* json: custom regex parser, adds dot support & JS-portable

* json: rm trailing spaces

* Update json-schema-to-grammar.mjs

* json: updated server & chat `( cd examples/server && ./deps.sh )`

* json: port fixes from mjs to python

* Update ts-type-to-grammar.sh

* json: support prefixItems alongside array items

* json: add date format + fix uuid

* json: add date, time, date-time formats

* json: preserve order of props from TS defs

* json: port schema converter to C++, wire in ./server

* json: nits

* Update json-schema-to-grammar.cpp

* Update json-schema-to-grammar.cpp

* Update json-schema-to-grammar.cpp

* json: fix mjs implementation + align outputs

* Update json-schema-to-grammar.mjs.hpp

* json: test C++, JS & Python versions

* json: nits + regen deps

* json: cleanup test

* json: revert from c++17 to 11

* json: nit fixes

* json: dirty include for test

* json: fix zig build

* json: pass static command to std::system in tests (fixed temp files)

* json: fix top-level $refs

* json: don't use c++20 designated initializers

* nit

* json: basic support for reserved names `{number:{number:{root:number}}}`

* Revamp test cmake to allow args (WORKING_DIRECTORY needed for JSON test)

* json: re-ran server deps.sh

* json: simplify test

* json: support mix of additional props & required/optional

* json: add tests for some expected failures

* json: fix type=const in c++, add failure expectations for non-str const&enum

* json: test (& simplify output of) empty schema

* json: check parsing in test + fix value & string refs

* json: add server tests for OAI JSON response_format

* json: test/fix top-level anyOf

* json: improve grammar parsing failures

* json: test/fix additional props corner cases

* json: fix string patterns (was missing quotes)

* json: ws nit

* json: fix json handling in server when there's no response_format

* json: catch schema conversion errors in server

* json: don't complain about unknown format type in server if unset

* json: cleaner build of test

* json: create examples/json-schema-pydantic-example.py

* json: fix date pattern

* json: move json.hpp & json-schema-to-grammar.{cpp,h} to common

* json: indent 4 spaces

* json: fix naming of top-level c++ function (+ drop unused one)

* json: avoid using namespace std

* json: fix zig build

* Update server.feature

* json: iostream -> fprintf

* json: space before & refs for consistency

* json: nits
2024-03-21 11:50:43 +00:00

78 lines
4.0 KiB
CMake

# 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_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 json-schema-to-grammar)
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()
# llama_test(test-double-float.cpp) # SLOW
llama_test(test-quantize-fns.cpp)
llama_test(test-quantize-perf.cpp)
llama_test(test-sampling.cpp)
llama_test(test-chat-template.cpp)
llama_test(test-tokenizer-0-llama.cpp NAME test-tokenizer-0-llama ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama.gguf)
llama_test(test-tokenizer-0-falcon.cpp NAME test-tokenizer-0-falcon ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-falcon.gguf)
llama_test(test-tokenizer-1-llama.cpp NAME test-tokenizer-1-llama ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama.gguf)
llama_test(test-tokenizer-1-llama.cpp NAME test-tokenizer-1-baichuan ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-baichuan.gguf)
llama_test(test-tokenizer-1-bpe.cpp NAME test-tokenizer-1-falcon ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-falcon.gguf)
llama_test(test-tokenizer-1-bpe.cpp NAME test-tokenizer-1-aquila ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-aquila.gguf)
llama_test(test-tokenizer-1-bpe.cpp NAME test-tokenizer-1-mpt ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-mpt.gguf)
llama_test(test-tokenizer-1-bpe.cpp NAME test-tokenizer-1-stablelm-3b-4e1t ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-stablelm-3b-4e1t.gguf)
llama_test(test-tokenizer-1-bpe.cpp NAME test-tokenizer-1-gpt-neox ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-neox.gguf)
llama_test(test-tokenizer-1-bpe.cpp NAME test-tokenizer-1-refact ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf)
llama_test(test-tokenizer-1-bpe.cpp NAME test-tokenizer-1-starcoder ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-starcoder.gguf)
llama_test(test-tokenizer-1-bpe.cpp NAME test-tokenizer-1-gpt2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt2.gguf)
#llama_test(test-tokenizer-1-bpe.cpp NAME test-tokenizer-1-bloom ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-bloom.gguf) # BIG
llama_test(test-grammar-parser.cpp)
llama_test(test-llama-grammar.cpp)
llama_test(test-grad0.cpp)
# llama_test(test-opt.cpp) # SLOW
llama_test(test-backend-ops.cpp)
llama_test(test-rope.cpp)
llama_test(test-model-load-cancel.cpp LABEL "model")
llama_test(test-autorelease.cpp LABEL "model")
llama_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)