thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

common : add nemotron 3 parsing (#18077)

Browse source 
* common : expose json-schema functionality to extract type info

* common : fix peg parser negation during needs_more_input

* common : add some defensive measures in constructed peg parser

* common : add nemotron nano 3 support

* common : add nemotron nano 3 tests

* remove debug line
This commit is contained in:
Aldehir Rojas 2025-12-16 04:05:23 -06:00 • committed by GitHub
parent 279cef27c2
commit c05aa69f32
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 741 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

157
tests/test-chat.cpp
View file

@ -3588,6 +3588,163 @@ static void test_template_output_peg_parsers() {
t.expect.content =R"({"amount": 123.45, "date": "2025-12-03"})";
});
}
{
// NVIDIA Nemotron-3 Nano
auto tmpls = read_templates("models/templates/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.jinja");
// Test basic message
test_peg_parser(tmpls.get(), [&](auto & t) {
t.input = "Hello, world!\nWhat's up?";
t.expect = message_assist;
});
// Test basic message and reasoning with reasoning_format = none
test_peg_parser(tmpls.get(), [&](auto & t) {
t.input = "I'm\nthinking\n</think>\nHello, world!\nWhat's up?";
t.expect.content = "I'm\nthinking\n</think>\nHello, world!\nWhat's up?";
});
// Test basic message and reasoning with reasoning_format = auto
test_peg_parser(tmpls.get(), [&](auto & t) {
t.input = "I'm\nthinking\n</think>\nHello, world!\nWhat's up?";
t.params.enable_thinking = true;
t.params.reasoning_format = COMMON_REASONING_FORMAT_AUTO;
t.expect = message_assist_thoughts;
});
// Test tool call
test_peg_parser(tmpls.get(), [&](auto & t) {
t.input =
"<tool_call>\n"
"<function=special_function>\n"
"<parameter=arg1>\n"
"1\n"
"</parameter>\n"
"</function>\n"
"</tool_call>";
t.params.enable_thinking = false;
t.params.reasoning_format = COMMON_REASONING_FORMAT_AUTO;
t.params.tools = {special_function_tool};
t.expect = message_assist_call;
});
// Test tool call with reasoning
test_peg_parser(tmpls.get(), [&](auto & t) {
t.input =
"I'm\nthinking\n</think>\n"
"<tool_call>\n"
"<function=special_function>\n"
"<parameter=arg1>\n"
"1\n"
"</parameter>\n"
"</function>\n"
"</tool_call>";
t.params.reasoning_format = COMMON_REASONING_FORMAT_AUTO;
t.params.tools = {special_function_tool};
t.expect = message_assist_call_thoughts;
});
// Test parallel tool calls
test_peg_parser(tmpls.get(), [&](auto & t) {
t.input =
"<tool_call>\n"
"<function=special_function>\n"
"<parameter=arg1>\n"
"1\n"
"</parameter>\n"
"</function>\n"
"</tool_call>\n"
"<tool_call>\n"
"<function=special_function_with_opt>\n"
"<parameter=arg1>\n"
"1\n"
"</parameter>\n"
"<parameter=arg2>\n"
"2\n"
"</parameter>\n"
"</function>\n"
"</tool_call>";
t.params.enable_thinking = false;
t.params.reasoning_format = COMMON_REASONING_FORMAT_AUTO;
t.params.parallel_tool_calls = true;
t.params.tools = {special_function_tool, special_function_tool_with_optional_param};
t.expect.tool_calls = {{
/* .name = */ "special_function",
/* .arguments = */ R"({"arg1": 1})",
/* .id = */ {},
}, {
/* .name = */ "special_function_with_opt",
/* .arguments = */ R"({"arg1": 1, "arg2": 2})",
/* .id = */ {},
}};
});
// Test tool call with string parameter
test_peg_parser(tmpls.get(), [&](auto & t) {
t.input =
"<tool_call>\n"
"<function=python>\n"
"<parameter=code>\n"
"def hello():\n"
" print(\"Hello, world!\")\n"
"\n"
"hello()\n"
"</parameter>\n"
"</function>\n"
"</tool_call>";
t.params.enable_thinking = false;
t.params.reasoning_format = COMMON_REASONING_FORMAT_AUTO;
t.params.tools = {python_tool};
t.expect.tool_calls = {{
/* .name = */ "python",
/* .arguments = */ "{\"code\": \"def hello():\\n print(\\\"Hello, world!\\\")\\n\\nhello()\"}",
/* .id = */ {},
}};
});
// Test tool call with string parameter and no closing </parameter> tag
test_peg_parser(tmpls.get(), [&](auto & t) {
t.input =
"<tool_call>\n"
"<function=python>\n"
"<parameter=code>\n"
"def hello():\n"
" print(\"Hello, world!\")\n"
"\n"
"hello()\n"
"</function>\n"
"</tool_call>";
t.params.enable_thinking = false;
t.params.reasoning_format = COMMON_REASONING_FORMAT_AUTO;
t.params.tools = {python_tool};
t.expect.tool_calls = {{
/* .name = */ "python",
/* .arguments = */ "{\"code\": \"def hello():\\n print(\\\"Hello, world!\\\")\\n\\nhello()\"}",
/* .id = */ {},
}};
});
// Test response format
test_peg_parser(tmpls.get(), [&](auto & t) {
t.input =
"I need to output the invoice details in JSON\n"
"</think>\n"
R"({"amount": 123.45, "date": "2025-12-03"})";
t.params.reasoning_format = COMMON_REASONING_FORMAT_AUTO;
t.params.json_schema = invoice_schema;
t.expect.reasoning_content = "I need to output the invoice details in JSON";
t.expect.content = R"({"amount": 123.45, "date": "2025-12-03"})";
});
}
}
static void test_msg_diffs_compute() {