mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-10-29 22:20:15 +01:00
Merge remote-tracking branch 'origin/master' into json-order
This commit is contained in:
commit
f286589a32
1
.github/workflows/build.yml
vendored
1
.github/workflows/build.yml
vendored
@ -799,6 +799,7 @@ jobs:
|
||||
7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/sde.tar
|
||||
$sde = $(join-path $env:RUNNER_TEMP sde-external-${env:SDE_VERSION}-win/sde.exe)
|
||||
cd build
|
||||
$env:LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR = 1
|
||||
& $sde -future -- ctest -L main -C Release --verbose --timeout 900
|
||||
|
||||
- name: Determine tag name
|
||||
|
@ -79,8 +79,15 @@ set(GGML_SANITIZE_ADDRESS ${LLAMA_SANITIZE_ADDRESS})
|
||||
set(GGML_SANITIZE_UNDEFINED ${LLAMA_SANITIZE_UNDEFINED})
|
||||
set(GGML_ALL_WARNINGS ${LLAMA_ALL_WARNINGS})
|
||||
set(GGML_FATAL_WARNINGS ${LLAMA_FATAL_WARNINGS})
|
||||
set(GGML_LLAMAFILE ON)
|
||||
set(GGML_CUDA_USE_GRAPHS ON)
|
||||
|
||||
# change the default for these ggml options
|
||||
if (NOT DEFINED GGML_LLAMAFILE)
|
||||
set(GGML_LLAMAFILE ON)
|
||||
endif()
|
||||
|
||||
if (NOT DEFINED GGML_CUDA_USE_GRAPHS)
|
||||
set(GGML_CUDA_USE_GRAPHS ON)
|
||||
endif()
|
||||
|
||||
# transition helpers
|
||||
function (llama_option_depr TYPE OLD NEW)
|
||||
|
@ -1026,6 +1026,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
|
||||
params.input_suffix = argv[i];
|
||||
return true;
|
||||
}
|
||||
if (arg == "--spm-infill") {
|
||||
params.spm_infill = true;
|
||||
return true;
|
||||
}
|
||||
if (arg == "--grammar") {
|
||||
CHECK_ARG
|
||||
sparams.grammar = argv[i];
|
||||
@ -1409,6 +1413,8 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
|
||||
options.push_back({ "main infill", " --in-prefix-bos", "prefix BOS to user inputs, preceding the `--in-prefix` string" });
|
||||
options.push_back({ "main infill", " --in-prefix STRING", "string to prefix user inputs with (default: empty)" });
|
||||
options.push_back({ "main infill", " --in-suffix STRING", "string to suffix after user inputs with (default: empty)" });
|
||||
options.push_back({ "server infill",
|
||||
" --spm-infill", "use Suffix/Prefix/Middle pattern for infill (instead of Prefix/Suffix/Middle) as some models prefer this. (default: %s)", params.spm_infill ? "enabled" : "disabled" });
|
||||
|
||||
options.push_back({ "sampling" });
|
||||
options.push_back({ "*", " --samplers SAMPLERS", "samplers that will be used for generation in the order, separated by \';\'\n"
|
||||
|
@ -250,6 +250,8 @@ struct gpt_params {
|
||||
std::string cvector_outfile = "control_vector.gguf";
|
||||
std::string cvector_positive_file = "examples/cvector-generator/positive.txt";
|
||||
std::string cvector_negative_file = "examples/cvector-generator/negative.txt";
|
||||
|
||||
bool spm_infill = false; // suffix/prefix/middle pattern for infill
|
||||
};
|
||||
|
||||
void gpt_params_handle_model_default(gpt_params & params);
|
||||
|
@ -15,6 +15,7 @@ In this section, we cover the most commonly used options for running the `infill
|
||||
- `-i, --interactive`: Run the program in interactive mode, allowing you to provide input directly and receive real-time responses.
|
||||
- `-n N, --n-predict N`: Set the number of tokens to predict when generating text. Adjusting this value can influence the length of the generated text.
|
||||
- `-c N, --ctx-size N`: Set the size of the prompt context. The default is 512, but LLaMA models were built with a context of 2048, which will provide better results for longer input/inference.
|
||||
- `--spm-infill`: Use Suffix/Prefix/Middle pattern for infill (instead of Prefix/Suffix/Middle) as some models prefer this.
|
||||
|
||||
## Input Prompts
|
||||
|
||||
|
@ -210,6 +210,7 @@ int main(int argc, char ** argv) {
|
||||
suff_rm_leading_spc = false;
|
||||
}
|
||||
std::vector<llama_token> embd_inp;
|
||||
std::vector<llama_token> embd_end;
|
||||
std::vector<llama_token> inp_pfx = ::llama_tokenize(ctx, params.input_prefix, false);
|
||||
std::vector<llama_token> inp_sfx = ::llama_tokenize(ctx, params.input_suffix, false);
|
||||
const int space_token = 29871;
|
||||
@ -217,12 +218,13 @@ int main(int argc, char ** argv) {
|
||||
inp_sfx.erase(inp_sfx.begin());
|
||||
}
|
||||
inp_pfx.insert(inp_pfx.begin(), llama_token_prefix(model));
|
||||
if (add_bos) {
|
||||
inp_pfx.insert(inp_pfx.begin(), llama_token_bos(model));
|
||||
}
|
||||
inp_sfx.insert(inp_sfx.begin(), llama_token_suffix(model));
|
||||
embd_inp = inp_pfx;
|
||||
embd_inp.insert(embd_inp.end(), inp_sfx.begin(), inp_sfx.end());
|
||||
embd_inp = params.spm_infill ? inp_sfx : inp_pfx;
|
||||
embd_end = params.spm_infill ? inp_pfx : inp_sfx;
|
||||
if (add_bos) {
|
||||
embd_inp.insert(embd_inp.begin(), llama_token_bos(model));
|
||||
}
|
||||
embd_inp.insert(embd_inp.end(), embd_end.begin(), embd_end.end());
|
||||
|
||||
const llama_token middle_token = llama_token_middle(model);
|
||||
if (middle_token >= 0) {
|
||||
@ -526,14 +528,14 @@ int main(int argc, char ** argv) {
|
||||
inp_sfx.erase(inp_sfx.begin());
|
||||
}
|
||||
inp_pfx.insert(inp_pfx.begin(), llama_token_prefix(model));
|
||||
if (add_bos) {
|
||||
inp_pfx.insert(inp_pfx.begin(), llama_token_bos(model));
|
||||
}
|
||||
inp_sfx.insert(inp_sfx.begin(), llama_token_suffix(model));
|
||||
embd_inp = inp_pfx;
|
||||
embd_inp.insert(embd_inp.end(), inp_sfx.begin(), inp_sfx.end());
|
||||
embd_inp = params.spm_infill ? inp_sfx : inp_pfx;
|
||||
embd_end = params.spm_infill ? inp_pfx : inp_sfx;
|
||||
if (add_bos) {
|
||||
embd_inp.insert(embd_inp.begin(), llama_token_bos(model));
|
||||
}
|
||||
embd_inp.insert(embd_inp.end(), embd_end.begin(), embd_end.end());
|
||||
|
||||
const llama_token middle_token = llama_token_middle(model);
|
||||
if (middle_token >= 0) {
|
||||
embd_inp.push_back(middle_token);
|
||||
}
|
||||
|
@ -73,6 +73,7 @@ The project is under active development, and we are [looking for feedback and co
|
||||
- `-fa`, `--flash-attn` : enable flash attention (default: disabled).
|
||||
- `-ctk TYPE`, `--cache-type-k TYPE` : KV cache data type for K (default: `f16`, options `f32`, `f16`, `q8_0`, `q4_0`, `q4_1`, `iq4_nl`, `q5_0`, or `q5_1`)
|
||||
- `-ctv TYPE`, `--cache-type-v TYPE` : KV cache type for V (default `f16`, see `-ctk` for options)
|
||||
- `--spm-infill` : Use Suffix/Prefix/Middle pattern for infill (instead of Prefix/Suffix/Middle) as some models prefer this.
|
||||
|
||||
**If compiled with `LLAMA_SERVER_SSL=ON`**
|
||||
- `--ssl-key-file FNAME`: path to file a PEM-encoded SSL private key
|
||||
|
@ -2020,6 +2020,7 @@ struct server_context {
|
||||
slot.t_start_generation = 0;
|
||||
|
||||
if (slot.infill) {
|
||||
const bool add_bos = llama_should_add_bos_token(model);
|
||||
bool suff_rm_leading_spc = true;
|
||||
if (params.input_suffix.find_first_of(' ') == 0 && params.input_suffix.size() > 1) {
|
||||
params.input_suffix.erase(0, 1);
|
||||
@ -2035,16 +2036,21 @@ struct server_context {
|
||||
}
|
||||
|
||||
prefix_tokens.insert(prefix_tokens.begin(), llama_token_prefix(model));
|
||||
prefix_tokens.insert(prefix_tokens.begin(), llama_token_bos(model)); // always add BOS
|
||||
prefix_tokens.insert(prefix_tokens.end(), llama_token_suffix(model));
|
||||
prefix_tokens.insert(prefix_tokens.end(), suffix_tokens.begin(), suffix_tokens.end());
|
||||
suffix_tokens.insert(suffix_tokens.begin(), llama_token_suffix(model));
|
||||
|
||||
auto embd_inp = params.spm_infill ? suffix_tokens : prefix_tokens;
|
||||
auto embd_end = params.spm_infill ? prefix_tokens : suffix_tokens;
|
||||
if (add_bos) {
|
||||
embd_inp.insert(embd_inp.begin(), llama_token_bos(model));
|
||||
}
|
||||
embd_inp.insert(embd_inp.end(), embd_end.begin(), embd_end.end());
|
||||
|
||||
const llama_token middle_token = llama_token_middle(model);
|
||||
if (middle_token >= 0) {
|
||||
prefix_tokens.push_back(middle_token);
|
||||
embd_inp.push_back(middle_token);
|
||||
}
|
||||
|
||||
prompt_tokens = prefix_tokens;
|
||||
prompt_tokens = embd_inp;
|
||||
} else {
|
||||
prompt_tokens = tokenize(slot.prompt, system_prompt.empty()); // add BOS if there isn't system prompt
|
||||
}
|
||||
|
@ -19613,7 +19613,10 @@ static int32_t llama_chat_apply_template_internal(
|
||||
std::string & dest, bool add_ass) {
|
||||
// Taken from the research: https://github.com/ggerganov/llama.cpp/issues/5527
|
||||
std::stringstream ss;
|
||||
if (tmpl == "chatml" || tmpl.find("<|im_start|>") != std::string::npos) {
|
||||
auto tmpl_contains = [&tmpl](std::string haystack) -> bool {
|
||||
return tmpl.find(haystack) != std::string::npos;
|
||||
};
|
||||
if (tmpl == "chatml" || tmpl_contains("<|im_start|>")) {
|
||||
// chatml template
|
||||
for (auto message : chat) {
|
||||
ss << "<|im_start|>" << message->role << "\n" << message->content << "<|im_end|>\n";
|
||||
@ -19621,16 +19624,16 @@ static int32_t llama_chat_apply_template_internal(
|
||||
if (add_ass) {
|
||||
ss << "<|im_start|>assistant\n";
|
||||
}
|
||||
} else if (tmpl == "llama2" || tmpl == "mistral" || tmpl.find("[INST]") != std::string::npos) {
|
||||
} else if (tmpl == "llama2" || tmpl == "mistral" || tmpl_contains("[INST]")) {
|
||||
// llama2 template and its variants
|
||||
// [variant] support system message
|
||||
bool support_system_message = tmpl.find("<<SYS>>") != std::string::npos || tmpl == "mistral";
|
||||
bool support_system_message = tmpl_contains("<<SYS>>") || tmpl == "mistral";
|
||||
// [variant] space before + after response
|
||||
bool space_around_response = tmpl.find("' ' + eos_token") != std::string::npos;
|
||||
bool space_around_response = tmpl_contains("' ' + eos_token");
|
||||
// [variant] add BOS inside history
|
||||
bool add_bos_inside_history = tmpl.find("bos_token + '[INST]") != std::string::npos;
|
||||
bool add_bos_inside_history = tmpl_contains("bos_token + '[INST]");
|
||||
// [variant] trim spaces from the input message
|
||||
bool strip_message = tmpl.find("content.strip()") != std::string::npos;
|
||||
bool strip_message = tmpl_contains("content.strip()");
|
||||
// construct the prompt
|
||||
bool is_inside_turn = true; // skip BOS at the beginning
|
||||
ss << "[INST] ";
|
||||
@ -19656,7 +19659,7 @@ static int32_t llama_chat_apply_template_internal(
|
||||
}
|
||||
}
|
||||
// llama2 templates seem to not care about "add_generation_prompt"
|
||||
} else if (tmpl == "phi3" || (tmpl.find("<|assistant|>") != std::string::npos && tmpl.find("<|end|>") != std::string::npos)) {
|
||||
} else if (tmpl == "phi3" || (tmpl_contains("<|assistant|>") && tmpl_contains("<|end|>"))) {
|
||||
// Phi 3
|
||||
for (auto message : chat) {
|
||||
std::string role(message->role);
|
||||
@ -19665,7 +19668,7 @@ static int32_t llama_chat_apply_template_internal(
|
||||
if (add_ass) {
|
||||
ss << "<|assistant|>\n";
|
||||
}
|
||||
} else if (tmpl == "zephyr" || tmpl.find("<|user|>") != std::string::npos) {
|
||||
} else if (tmpl == "zephyr" || tmpl_contains("<|user|>")) {
|
||||
// zephyr template
|
||||
for (auto message : chat) {
|
||||
ss << "<|" << message->role << "|>" << "\n" << message->content << "<|endoftext|>\n";
|
||||
@ -19673,7 +19676,7 @@ static int32_t llama_chat_apply_template_internal(
|
||||
if (add_ass) {
|
||||
ss << "<|assistant|>\n";
|
||||
}
|
||||
} else if (tmpl == "monarch" || tmpl.find("bos_token + message['role']") != std::string::npos) {
|
||||
} else if (tmpl == "monarch" || tmpl_contains("bos_token + message['role']")) {
|
||||
// mlabonne/AlphaMonarch-7B template (the <s> is included inside history)
|
||||
for (auto message : chat) {
|
||||
std::string bos = (message == chat.front()) ? "" : "<s>"; // skip BOS for first message
|
||||
@ -19682,7 +19685,7 @@ static int32_t llama_chat_apply_template_internal(
|
||||
if (add_ass) {
|
||||
ss << "<s>assistant\n";
|
||||
}
|
||||
} else if (tmpl == "gemma" || tmpl == "gemma2" || tmpl.find("<start_of_turn>") != std::string::npos) {
|
||||
} else if (tmpl == "gemma" || tmpl == "gemma2" || tmpl_contains("<start_of_turn>")) {
|
||||
// google/gemma-7b-it
|
||||
std::string system_prompt = "";
|
||||
for (auto message : chat) {
|
||||
@ -19704,7 +19707,7 @@ static int32_t llama_chat_apply_template_internal(
|
||||
if (add_ass) {
|
||||
ss << "<start_of_turn>model\n";
|
||||
}
|
||||
} else if (tmpl == "orion" || tmpl.find("'\\n\\nAssistant: ' + eos_token") != std::string::npos) {
|
||||
} else if (tmpl == "orion" || tmpl_contains("'\\n\\nAssistant: ' + eos_token")) {
|
||||
// OrionStarAI/Orion-14B-Chat
|
||||
std::string system_prompt = "";
|
||||
for (auto message : chat) {
|
||||
@ -19724,7 +19727,7 @@ static int32_t llama_chat_apply_template_internal(
|
||||
ss << message->content << "</s>";
|
||||
}
|
||||
}
|
||||
} else if (tmpl == "openchat" || tmpl.find("GPT4 Correct ") != std::string::npos) {
|
||||
} else if (tmpl == "openchat" || tmpl_contains("GPT4 Correct ")) {
|
||||
// openchat/openchat-3.5-0106,
|
||||
for (auto message : chat) {
|
||||
std::string role(message->role);
|
||||
@ -19738,13 +19741,13 @@ static int32_t llama_chat_apply_template_internal(
|
||||
if (add_ass) {
|
||||
ss << "GPT4 Correct Assistant:";
|
||||
}
|
||||
} else if (tmpl == "vicuna" || tmpl == "vicuna-orca" || (tmpl.find("USER: ") != std::string::npos && tmpl.find("ASSISTANT: ") != std::string::npos)) {
|
||||
} else if (tmpl == "vicuna" || tmpl == "vicuna-orca" || (tmpl_contains("USER: ") && tmpl_contains("ASSISTANT: "))) {
|
||||
// eachadea/vicuna-13b-1.1 (and Orca variant)
|
||||
for (auto message : chat) {
|
||||
std::string role(message->role);
|
||||
if (role == "system") {
|
||||
// Orca-Vicuna variant uses a system prefix
|
||||
if (tmpl == "vicuna-orca" || tmpl.find("SYSTEM: ") != std::string::npos) {
|
||||
if (tmpl == "vicuna-orca" || tmpl_contains("SYSTEM: ")) {
|
||||
ss << "SYSTEM: " << message->content << "\n";
|
||||
} else {
|
||||
ss << message->content << "\n\n";
|
||||
@ -19758,7 +19761,7 @@ static int32_t llama_chat_apply_template_internal(
|
||||
if (add_ass) {
|
||||
ss << "ASSISTANT:";
|
||||
}
|
||||
} else if (tmpl == "deepseek" || (tmpl.find("### Instruction:") != std::string::npos && tmpl.find("<|EOT|>") != std::string::npos)) {
|
||||
} else if (tmpl == "deepseek" || (tmpl_contains("### Instruction:") && tmpl_contains("<|EOT|>"))) {
|
||||
// deepseek-ai/deepseek-coder-33b-instruct
|
||||
for (auto message : chat) {
|
||||
std::string role(message->role);
|
||||
@ -19773,7 +19776,7 @@ static int32_t llama_chat_apply_template_internal(
|
||||
if (add_ass) {
|
||||
ss << "### Response:\n";
|
||||
}
|
||||
} else if (tmpl == "command-r" || (tmpl.find("<|START_OF_TURN_TOKEN|>") != std::string::npos && tmpl.find("<|USER_TOKEN|>") != std::string::npos)) {
|
||||
} else if (tmpl == "command-r" || (tmpl_contains("<|START_OF_TURN_TOKEN|>") && tmpl_contains("<|USER_TOKEN|>"))) {
|
||||
// CohereForAI/c4ai-command-r-plus
|
||||
for (auto message : chat) {
|
||||
std::string role(message->role);
|
||||
@ -19788,7 +19791,7 @@ static int32_t llama_chat_apply_template_internal(
|
||||
if (add_ass) {
|
||||
ss << "<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>";
|
||||
}
|
||||
} else if (tmpl == "llama3" || (tmpl.find("<|start_header_id|>") != std::string::npos && tmpl.find("<|end_header_id|>") != std::string::npos)) {
|
||||
} else if (tmpl == "llama3" || (tmpl_contains("<|start_header_id|>") && tmpl_contains("<|end_header_id|>"))) {
|
||||
// Llama 3
|
||||
for (auto message : chat) {
|
||||
std::string role(message->role);
|
||||
@ -19797,6 +19800,33 @@ static int32_t llama_chat_apply_template_internal(
|
||||
if (add_ass) {
|
||||
ss << "<|start_header_id|>assistant<|end_header_id|>\n\n";
|
||||
}
|
||||
} else if (tmpl == "minicpm" || tmpl_contains(u8"<用户>")) {
|
||||
// MiniCPM-3B-OpenHermes-2.5-v2-GGUF
|
||||
for (auto message : chat) {
|
||||
std::string role(message->role);
|
||||
if (role == "user") {
|
||||
ss << u8"<用户>";
|
||||
ss << trim(message->content);
|
||||
ss << "<AI>";
|
||||
} else {
|
||||
ss << trim(message->content);
|
||||
}
|
||||
}
|
||||
} else if (tmpl == "deepseek2" || tmpl_contains("'Assistant: ' + message['content'] + eos_token")) {
|
||||
// DeepSeek-V2
|
||||
for (auto message : chat) {
|
||||
std::string role(message->role);
|
||||
if (role == "system") {
|
||||
ss << message->content << "\n\n";
|
||||
} else if (role == "user") {
|
||||
ss << "User: " << message->content << "\n\n";
|
||||
} else if (role == "assistant") {
|
||||
ss << "Assistant: " << message->content << u8"<|end▁of▁sentence|>";
|
||||
}
|
||||
}
|
||||
if (add_ass) {
|
||||
ss << "Assistant:";
|
||||
}
|
||||
} else {
|
||||
// template not supported
|
||||
return -1;
|
||||
|
@ -57,7 +57,11 @@ int main(void) {
|
||||
//Phi-3-medium
|
||||
"{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
||||
//Phi-3-vision
|
||||
"{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '<|assistant|>\n' -}}{% endif %}"
|
||||
"{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '<|assistant|>\n' -}}{% endif %}",
|
||||
// MiniCPM-3B-OpenHermes-2.5-v2-GGUF
|
||||
u8"{% for message in messages %}{% if message['role'] == 'user' %}{{'<用户>' + message['content'].strip() + '<AI>'}}{% else %}{{message['content'].strip()}}{% endif %}{% endfor %}",
|
||||
// DeepSeek-V2
|
||||
"{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
|
||||
};
|
||||
std::vector<std::string> expected_output = {
|
||||
// teknium/OpenHermes-2.5-Mistral-7B
|
||||
@ -94,6 +98,10 @@ int main(void) {
|
||||
"<|system|>\nYou are a helpful assistant<|end|>\n<|user|>\nHello<|end|>\n<|assistant|>\nHi there<|end|>\n<|user|>\nWho are you<|end|>\n<|assistant|>\n I am an assistant <|end|>\n<|user|>\nAnother question<|end|>\n<|assistant|>\n",
|
||||
//Phi-3-vision
|
||||
"<|system|>\nYou are a helpful assistant<|end|>\n<|user|>\nHello<|end|>\n<|assistant|>\nHi there<|end|>\n<|user|>\nWho are you<|end|>\n<|assistant|>\n I am an assistant <|end|>\n<|user|>\nAnother question<|end|>\n<|assistant|>\n",
|
||||
// MiniCPM-3B-OpenHermes-2.5-v2-GGUF
|
||||
u8"You are a helpful assistant<用户>Hello<AI>Hi there<用户>Who are you<AI>I am an assistant<用户>Another question<AI>",
|
||||
// DeepSeek-V2
|
||||
u8"You are a helpful assistant\n\nUser: Hello\n\nAssistant: Hi there<|end▁of▁sentence|>User: Who are you\n\nAssistant: I am an assistant <|end▁of▁sentence|>User: Another question\n\nAssistant:",
|
||||
};
|
||||
std::vector<char> formatted_chat(1024);
|
||||
int32_t res;
|
||||
|
@ -1247,26 +1247,30 @@ int main() {
|
||||
}
|
||||
});
|
||||
|
||||
if (getenv("LLAMA_PYTHON_AVAILABLE") || (std::system("python -c \"import sys; exit(1) if sys.version_info < (3, 8) else print('Python version is sufficient')\"") == 0)) {
|
||||
test_all("Python", [](const TestCase & tc) {
|
||||
write("test-json-schema-input.tmp", tc.schema);
|
||||
tc.verify_status(std::system(
|
||||
"python ./examples/json_schema_to_grammar.py test-json-schema-input.tmp > test-grammar-output.tmp") == 0 ? SUCCESS : FAILURE);
|
||||
tc.verify(read("test-grammar-output.tmp"));
|
||||
});
|
||||
if (getenv("LLAMA_SKIP_TESTS_SLOW_ON_EMULATOR")) {
|
||||
fprintf(stderr, "\033[33mWARNING: Skipping slow tests on emulator.\n\033[0m");
|
||||
} else {
|
||||
fprintf(stderr, "\033[33mWARNING: Python not found (min version required is 3.8), skipping Python JSON schema -> grammar tests.\n\033[0m");
|
||||
}
|
||||
if (getenv("LLAMA_PYTHON_AVAILABLE") || (std::system("python -c \"import sys; exit(1) if sys.version_info < (3, 8) else print('Python version is sufficient')\"") == 0)) {
|
||||
test_all("Python", [](const TestCase & tc) {
|
||||
write("test-json-schema-input.tmp", tc.schema);
|
||||
tc.verify_status(std::system(
|
||||
"python ./examples/json_schema_to_grammar.py test-json-schema-input.tmp > test-grammar-output.tmp") == 0 ? SUCCESS : FAILURE);
|
||||
tc.verify(read("test-grammar-output.tmp"));
|
||||
});
|
||||
} else {
|
||||
fprintf(stderr, "\033[33mWARNING: Python not found (min version required is 3.8), skipping Python JSON schema -> grammar tests.\n\033[0m");
|
||||
}
|
||||
|
||||
if (getenv("LLAMA_NODE_AVAILABLE") || (std::system("node --version") == 0)) {
|
||||
test_all("JavaScript", [](const TestCase & tc) {
|
||||
write("test-json-schema-input.tmp", tc.schema);
|
||||
tc.verify_status(std::system(
|
||||
"node ./tests/run-json-schema-to-grammar.mjs test-json-schema-input.tmp > test-grammar-output.tmp") == 0 ? SUCCESS : FAILURE);
|
||||
tc.verify(read("test-grammar-output.tmp"));
|
||||
});
|
||||
} else {
|
||||
fprintf(stderr, "\033[33mWARNING: Node not found, skipping JavaScript JSON schema -> grammar tests.\n\033[0m");
|
||||
if (getenv("LLAMA_NODE_AVAILABLE") || (std::system("node --version") == 0)) {
|
||||
test_all("JavaScript", [](const TestCase & tc) {
|
||||
write("test-json-schema-input.tmp", tc.schema);
|
||||
tc.verify_status(std::system(
|
||||
"node ./tests/run-json-schema-to-grammar.mjs test-json-schema-input.tmp > test-grammar-output.tmp") == 0 ? SUCCESS : FAILURE);
|
||||
tc.verify(read("test-grammar-output.tmp"));
|
||||
});
|
||||
} else {
|
||||
fprintf(stderr, "\033[33mWARNING: Node not found, skipping JavaScript JSON schema -> grammar tests.\n\033[0m");
|
||||
}
|
||||
}
|
||||
|
||||
test_all("Check Expectations Validity", [](const TestCase & tc) {
|
||||
|
Loading…
Reference in New Issue
Block a user