@fugood/llama.node 0.6.2 → 1.0.0-beta.1

package/src/llama.cpp/requirements/requirements-convert_hf_to_gguf_update.txt

@@ -1,7 +0,0 @@
--r ./requirements-convert_legacy_llama.txt
---extra-index-url https://download.pytorch.org/whl/cpu
-torch~=2.2.1; platform_machine != "s390x"
-
-# torch s390x packages can only be found from nightly builds
---extra-index-url https://download.pytorch.org/whl/nightly
-torch>=0.0.0.dev0; platform_machine == "s390x"

package/src/llama.cpp/requirements/requirements-convert_legacy_llama.txt

@@ -1,5 +0,0 @@
-numpy~=1.26.4
-sentencepiece~=0.2.0
-transformers>=4.45.1,<5.0.0
-gguf>=0.1.0
-protobuf>=4.21.0,<5.0.0

package/src/llama.cpp/requirements/requirements-convert_llama_ggml_to_gguf.txt

@@ -1 +0,0 @@
--r ./requirements-convert_legacy_llama.txt

package/src/llama.cpp/requirements/requirements-convert_lora_to_gguf.txt

@@ -1,4 +0,0 @@
--r ./requirements-convert_hf_to_gguf.txt
---extra-index-url https://download.pytorch.org/whl/cpu
-# torch s390x packages can only be found from nightly builds
---extra-index-url https://download.pytorch.org/whl/nightly

package/src/llama.cpp/requirements/requirements-gguf_editor_gui.txt

@@ -1,3 +0,0 @@
-numpy~=1.26.4
-PySide6~=6.9.0
-gguf>=0.16.0

package/src/llama.cpp/requirements/requirements-pydantic.txt

@@ -1,3 +0,0 @@
-docstring_parser~=0.15
-pydantic~=2.6.3
-requests

package/src/llama.cpp/requirements/requirements-test-tokenizer-random.txt

@@ -1 +0,0 @@
-cffi~=1.16.0

package/src/llama.cpp/requirements/requirements-tool_bench.txt

@@ -1,12 +0,0 @@
-aiohttp~=3.9.3
-pytest~=8.3.3
-huggingface_hub~=0.23.2
-matplotlib~=3.10.0
-numpy~=1.26.4
-openai~=1.55.3
-pandas~=2.2.3
-prometheus-client~=0.20.0
-requests~=2.32.3
-wget~=3.2
-typer~=0.15.1
-seaborn~=0.13.2

package/src/llama.cpp/requirements.txt

@@ -1,13 +0,0 @@
-# These requirements include all dependencies for all top-level python scripts
-# for llama.cpp. Avoid adding packages here directly.
-#
-# Package versions must stay compatible across all top-level python scripts.
-#
-
--r ./requirements/requirements-convert_legacy_llama.txt
-
--r ./requirements/requirements-convert_hf_to_gguf.txt
--r ./requirements/requirements-convert_hf_to_gguf_update.txt
--r ./requirements/requirements-convert_llama_ggml_to_gguf.txt
--r ./requirements/requirements-convert_lora_to_gguf.txt
--r ./requirements/requirements-tool_bench.txt

package/src/llama.cpp/scripts/build-info.sh

@@ -1,30 +0,0 @@
-#!/bin/sh
-
-CC=$1
-
-build_number="0"
-build_commit="unknown"
-build_compiler="unknown"
-build_target="unknown"
-
-if out=$(git rev-list --count HEAD); then
-    # git is broken on WSL so we need to strip extra newlines
-    build_number=$(printf '%s' "$out" | tr -d '\n')
-fi
-
-if out=$(git rev-parse --short HEAD); then
-    build_commit=$(printf '%s' "$out" | tr -d '\n')
-fi
-
-if out=$($CC --version | head -1); then
-    build_compiler=$out
-fi
-
-if out=$($CC -dumpmachine); then
-    build_target=$out
-fi
-
-echo "int LLAMA_BUILD_NUMBER = ${build_number};"
-echo "char const *LLAMA_COMMIT = \"${build_commit}\";"
-echo "char const *LLAMA_COMPILER = \"${build_compiler}\";"
-echo "char const *LLAMA_BUILD_TARGET = \"${build_target}\";"

package/src/llama.cpp/scripts/install-oneapi.bat

@@ -1,19 +0,0 @@
-::  MIT license
-::  Copyright (C) 2024 Intel Corporation
-::  SPDX-License-Identifier: MIT
-
-
-set URL=%1
-set COMPONENTS=%2
-
-curl.exe --output %TEMP%\webimage.exe --url %URL% --retry 5 --retry-delay 5
-start /b /wait %TEMP%\webimage.exe -s -x -f webimage_extracted --log extract.log
-del %TEMP%\webimage.exe
-if "%COMPONENTS%"=="" (
-  webimage_extracted\bootstrapper.exe -s --action install --eula=accept -p=NEED_VS2017_INTEGRATION=0 -p=NEED_VS2019_INTEGRATION=0 -p=NEED_VS2022_INTEGRATION=0 --log-dir=.
-) else (
-  webimage_extracted\bootstrapper.exe -s --action install --components=%COMPONENTS% --eula=accept -p=NEED_VS2017_INTEGRATION=0 -p=NEED_VS2019_INTEGRATION=0 -p=NEED_VS2022_INTEGRATION=0 --log-dir=.
-)
-set installer_exit_code=%ERRORLEVEL%
-rd /s/q "webimage_extracted"
-exit /b %installer_exit_code%

package/src/llama.cpp/scripts/xxd.cmake

@@ -1,16 +0,0 @@
-# CMake equivalent of `xxd -i ${INPUT} ${OUTPUT}`
-# Usage: cmake -DINPUT=tools/server/public/index.html -DOUTPUT=tools/server/index.html.hpp -P scripts/xxd.cmake
-
-SET(INPUT "" CACHE STRING "Input File")
-SET(OUTPUT "" CACHE STRING "Output File")
-
-get_filename_component(filename "${INPUT}" NAME)
-string(REGEX REPLACE "\\.|-" "_" name "${filename}")
-
-file(READ "${INPUT}" hex_data HEX)
-string(REGEX REPLACE "([0-9a-f][0-9a-f])" "0x\\1," hex_sequence "${hex_data}")
-
-string(LENGTH ${hex_data} hex_len)
-math(EXPR len "${hex_len} / 2")
-
-file(WRITE "${OUTPUT}" "unsigned char ${name}[] = {${hex_sequence}};\nunsigned int ${name}_len = ${len};\n")

package/src/llama.cpp/tests/CMakeLists.txt

@@ -1,177 +0,0 @@
-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 ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-baichuan.gguf)
-
-    # llama_build_and_test(test-double-float.cpp) # SLOW
-endif()
-
-llama_build_and_test(test-log.cpp)
-llama_build_and_test(test-chat-template.cpp)
-llama_build_and_test(test-regex-partial.cpp)
-
-# this fails on windows (github hosted runner) due to curl DLL not found (exit code 0xc0000135)
-if (NOT WIN32)
-    llama_build_and_test(test-arg-parser.cpp)
-endif()
-
-# llama_build_and_test(test-opt.cpp) # SLOW
-llama_build_and_test(test-gguf.cpp)
-llama_build_and_test(test-backend-ops.cpp)
-
-llama_build_and_test(test-model-load-cancel.cpp  LABEL "model")
-llama_build_and_test(test-autorelease.cpp        LABEL "model")
-
-if (NOT GGML_BACKEND_DL)
-    # these tests use the backends directly and cannot be built with dynamic loading
-    llama_build_and_test(test-barrier.cpp)
-    llama_build_and_test(test-quantize-fns.cpp)
-    llama_build_and_test(test-quantize-perf.cpp)
-    llama_build_and_test(test-rope.cpp)
-endif()
-
-# libmtmd
-set(LLAMA_TEST_NAME test-mtmd-c-api)
-llama_build_and_test(test-mtmd-c-api.c)
-target_link_libraries(${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)

package/src/llama.cpp/tests/get-model.cpp

@@ -1,21 +0,0 @@
-#include <cstdio>
-#include <cstdlib>
-#include <cstring>
-
-#include "get-model.h"
-
-char * get_model_or_exit(int argc, char *argv[]) {
-    char * model_path;
-    if (argc > 1) {
-        model_path = argv[1];
-
-    } else {
-        model_path = getenv("LLAMACPP_TEST_MODELFILE");
-        if (!model_path || strlen(model_path) == 0) {
-            fprintf(stderr, "\033[33mWARNING: No model file provided. Skipping this test. Set LLAMACPP_TEST_MODELFILE=<gguf_model_path> to silence this warning and run this test.\n\033[0m");
-            exit(EXIT_SUCCESS);
-        }
-    }
-
-    return model_path;
-}

package/src/llama.cpp/tests/get-model.h

@@ -1,2 +0,0 @@
-#pragma once
-char * get_model_or_exit(int, char*[]);

package/src/llama.cpp/tests/test-arg-parser.cpp

@@ -1,178 +0,0 @@
-#include "arg.h"
-#include "common.h"
-
-#include <string>
-#include <vector>
-#include <sstream>
-#include <unordered_set>
-
-#undef NDEBUG
-#include <cassert>
-
-int main(void) {
-    common_params params;
-
-    printf("test-arg-parser: make sure there is no duplicated arguments in any examples\n\n");
-    for (int ex = 0; ex < LLAMA_EXAMPLE_COUNT; ex++) {
-        try {
-            auto ctx_arg = common_params_parser_init(params, (enum llama_example)ex);
-            std::unordered_set<std::string> seen_args;
-            std::unordered_set<std::string> seen_env_vars;
-            for (const auto & opt : ctx_arg.options) {
-                // check for args duplications
-                for (const auto & arg : opt.args) {
-                    if (seen_args.find(arg) == seen_args.end()) {
-                        seen_args.insert(arg);
-                    } else {
-                        fprintf(stderr, "test-arg-parser: found different handlers for the same argument: %s", arg);
-                        exit(1);
-                    }
-                }
-                // check for env var duplications
-                if (opt.env) {
-                    if (seen_env_vars.find(opt.env) == seen_env_vars.end()) {
-                        seen_env_vars.insert(opt.env);
-                    } else {
-                        fprintf(stderr, "test-arg-parser: found different handlers for the same env var: %s", opt.env);
-                        exit(1);
-                    }
-                }
-            }
-        } catch (std::exception & e) {
-            printf("%s\n", e.what());
-            assert(false);
-        }
-    }
-
-    auto list_str_to_char = [](std::vector<std::string> & argv) -> std::vector<char *> {
-        std::vector<char *> res;
-        for (auto & arg : argv) {
-            res.push_back(const_cast<char *>(arg.data()));
-        }
-        return res;
-    };
-
-    std::vector<std::string> argv;
-
-    printf("test-arg-parser: test invalid usage\n\n");
-
-    // missing value
-    argv = {"binary_name", "-m"};
-    assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
-
-    // wrong value (int)
-    argv = {"binary_name", "-ngl", "hello"};
-    assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
-
-    // wrong value (enum)
-    argv = {"binary_name", "-sm", "hello"};
-    assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
-
-    // non-existence arg in specific example (--draft cannot be used outside llama-speculative)
-    argv = {"binary_name", "--draft", "123"};
-    assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_EMBEDDING));
-
-
-    printf("test-arg-parser: test valid usage\n\n");
-
-    argv = {"binary_name", "-m", "model_file.gguf"};
-    assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
-    assert(params.model.path == "model_file.gguf");
-
-    argv = {"binary_name", "-t", "1234"};
-    assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
-    assert(params.cpuparams.n_threads == 1234);
-
-    argv = {"binary_name", "--verbose"};
-    assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
-    assert(params.verbosity > 1);
-
-    argv = {"binary_name", "-m", "abc.gguf", "--predict", "6789", "--batch-size", "9090"};
-    assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
-    assert(params.model.path == "abc.gguf");
-    assert(params.n_predict == 6789);
-    assert(params.n_batch == 9090);
-
-    // --draft cannot be used outside llama-speculative
-    argv = {"binary_name", "--draft", "123"};
-    assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_SPECULATIVE));
-    assert(params.speculative.n_max == 123);
-
-// skip this part on windows, because setenv is not supported
-#ifdef _WIN32
-    printf("test-arg-parser: skip on windows build\n");
-#else
-    printf("test-arg-parser: test environment variables (valid + invalid usages)\n\n");
-
-    setenv("LLAMA_ARG_THREADS", "blah", true);
-    argv = {"binary_name"};
-    assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
-
-    setenv("LLAMA_ARG_MODEL", "blah.gguf", true);
-    setenv("LLAMA_ARG_THREADS", "1010", true);
-    argv = {"binary_name"};
-    assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
-    assert(params.model.path == "blah.gguf");
-    assert(params.cpuparams.n_threads == 1010);
-
-
-    printf("test-arg-parser: test environment variables being overwritten\n\n");
-
-    setenv("LLAMA_ARG_MODEL", "blah.gguf", true);
-    setenv("LLAMA_ARG_THREADS", "1010", true);
-    argv = {"binary_name", "-m", "overwritten.gguf"};
-    assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON));
-    assert(params.model.path == "overwritten.gguf");
-    assert(params.cpuparams.n_threads == 1010);
-#endif // _WIN32
-
-    if (common_has_curl()) {
-        printf("test-arg-parser: test curl-related functions\n\n");
-        const char * GOOD_URL = "https://ggml.ai/";
-        const char * BAD_URL  = "https://www.google.com/404";
-        const char * BIG_FILE = "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v1.bin";
-
-        {
-            printf("test-arg-parser: test good URL\n\n");
-            auto res = common_remote_get_content(GOOD_URL, {});
-            assert(res.first == 200);
-            assert(res.second.size() > 0);
-            std::string str(res.second.data(), res.second.size());
-            assert(str.find("llama.cpp") != std::string::npos);
-        }
-
-        {
-            printf("test-arg-parser: test bad URL\n\n");
-            auto res = common_remote_get_content(BAD_URL, {});
-            assert(res.first == 404);
-        }
-
-        {
-            printf("test-arg-parser: test max size error\n");
-            common_remote_params params;
-            params.max_size = 1;
-            try {
-                common_remote_get_content(GOOD_URL, params);
-                assert(false && "it should throw an error");
-            } catch (std::exception & e) {
-                printf("  expected error: %s\n\n", e.what());
-            }
-        }
-
-        {
-            printf("test-arg-parser: test timeout error\n");
-            common_remote_params params;
-            params.timeout = 1;
-            try {
-                common_remote_get_content(BIG_FILE, params);
-                assert(false && "it should throw an error");
-            } catch (std::exception & e) {
-                printf("  expected error: %s\n\n", e.what());
-            }
-        }
-    } else {
-        printf("test-arg-parser: no curl, skipping curl-related functions\n");
-    }
-
-    printf("test-arg-parser: all tests OK\n\n");
-}

package/src/llama.cpp/tests/test-autorelease.cpp

@@ -1,24 +0,0 @@
-// ref: https://github.com/ggerganov/llama.cpp/issues/4952#issuecomment-1892864763
-
-#include <cstdio>
-#include <string>
-#include <thread>
-
-#include "llama.h"
-#include "get-model.h"
-
-// This creates a new context inside a pthread and then tries to exit cleanly.
-int main(int argc, char ** argv) {
-    auto * model_path = get_model_or_exit(argc, argv);
-
-    std::thread([&model_path]() {
-        llama_backend_init();
-        auto * model = llama_model_load_from_file(model_path, llama_model_default_params());
-        auto * ctx = llama_init_from_model(model, llama_context_default_params());
-        llama_free(ctx);
-        llama_model_free(model);
-        llama_backend_free();
-    }).join();
-
-    return 0;
-}