happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'ggml-org:master' into master

This commit is contained in:
Kusha Gharahi 2026-03-06 15:34:42 -06:00 committed by GitHub
parent 0d83366970 2f2923f895
commit 04b71f6fba
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 128 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
common/chat-auto-parser-generator.cpp
View File

@ -302,8 +302,9 @@ common_peg_parser analyze_tools::build_tool_parser_tag_tagged(parser_build_conte
params.at("required").get_to(required);
}
// Build parser for each argument
std::vector<common_peg_parser> arg_parsers;
// Build parser for each argument, separating required and optional
std::vector<common_peg_parser> required_parsers;
std::vector<common_peg_parser> optional_parsers;
for (const auto & [param_name, param_schema] : properties.items()) {
bool is_required = required.find(param_name) != required.end();
std::string type = "object";
@ -328,20 +329,30 @@ common_peg_parser analyze_tools::build_tool_parser_tag_tagged(parser_build_conte
p.space()) +
p.tool_arg_close(p.literal(arguments.value_suffix)));
auto named_arg = p.rule("tool-" + name + "-arg-" + param_name, arg);
if (is_required) {
arg_parsers.push_back(p.rule("tool-" + name + "-arg-" + param_name, arg));
required_parsers.push_back(named_arg);
} else {
arg_parsers.push_back(p.optional(p.rule("tool-" + name + "-arg-" + param_name, arg)));
optional_parsers.push_back(named_arg);
}
}
// Build arg sequence with space() between consecutive args
// Build required arg sequence in definition order
common_peg_parser args_seq = p.eps();
for (size_t i = 0; i < arg_parsers.size(); i++) {
for (size_t i = 0; i < required_parsers.size(); i++) {
if (i > 0) {
args_seq = args_seq + p.space();
}
args_seq = args_seq + arg_parsers[i];
args_seq = args_seq + required_parsers[i];
}
// Build optional args with flexible ordering
if (!optional_parsers.empty()) {
common_peg_parser any_opt = p.choice();
for (const auto & opt : optional_parsers) {
any_opt |= opt;
}
args_seq = args_seq + p.repeat(p.space() + any_opt, 0, (int) optional_parsers.size());
}
// Build call_id parser based on position (if supported)

27
ggml/src/ggml-quants.c
View File

@ -3104,6 +3104,11 @@ static void quantize_row_iq2_xxs_impl(const float * GGML_RESTRICT x, void * GGML
}
float scale = make_qp_quants(32, kMaxQ+1, xval, (uint8_t*)L, weight);
float eff_max = scale*kMaxQ;
if (eff_max <= 0) {
scales[ib] = 0;
memset(L, 0, 32);
continue;
}
float best = 0;
for (int is = -6; is <= 6; ++is) {
float id = (2*kMaxQ-1+is*0.1f)/eff_max;
@ -3273,9 +3278,9 @@ static void quantize_row_iq2_xs_impl(const float * GGML_RESTRICT x, void * GGML_
}
float max = xval[0];
for (int i = 1; i < 16; ++i) max = MAX(max, xval[i]);
memset(L, 0, 16);
if (max < GROUP_MAX_EPS) {
scales[ib] = 0;
memset(L, 0, 16);
continue;
}
float best = 0;
@ -3714,9 +3719,9 @@ static void quantize_row_iq3_xxs_impl(int grid_size, const float * GGML_RESTRICT
}
float max = xval[0];
for (int i = 1; i < 32; ++i) max = MAX(max, xval[i]);
memset(L, 0, 32);
if (max < GROUP_MAX_EPS_IQ3_XXS) {
scales[ib] = 0;
memset(L, 0, 32);
continue;
}
float best = 0;
@ -3922,6 +3927,7 @@ static void quantize_row_iq3_s_impl(int block_size, const float * GGML_RESTRICT
}
float max = xval[0];
for (int i = 1; i < block_size; ++i) max = MAX(max, xval[i]);
memset(L, 0, block_size);
if (!max) {
scales[ib] = 0;
continue;
@ -4245,6 +4251,7 @@ static void quantize_row_iq1_s_impl(const float * GGML_RESTRICT x, void * GGML_R
for (int i = 1; i < block_size; ++i) max = MAX(max, fabsf(xb[i]));
if (max < GROUP_MAX_EPS_IQ1_S) {
scales[ib] = 0;
shifts[ib] = 1;
memset(L, 1, block_size);
continue;
}
@ -4285,7 +4292,12 @@ static void quantize_row_iq1_s_impl(const float * GGML_RESTRICT x, void * GGML_R
}
}
}
GGML_ASSERT(besti1 >= 0 && besti2 >= 0 && best_shift != 0);
if (besti1 < 0 || besti2 < 0 || best_shift == 0) {
scales[ib] = 0;
shifts[ib] = 1;
memset(L, 1, block_size);
continue;
}
for (int j = 0; j < besti1; ++j) L[idx[2*j]] = 0;
for (int j = besti1; j < besti2; ++j) L[idx[2*j]] = 1;
for (int j = besti2; j < block_size; ++j) L[idx[2*j]] = 2;
@ -4429,6 +4441,7 @@ static void quantize_row_iq1_m_impl(const float * GGML_RESTRICT x, void * GGML_R
for (int i = 1; i < block_size; ++i) max = MAX(max, fabsf(xb[i]));
if (max < GROUP_MAX_EPS_IQ1_M) {
scales[ib] = 0;
shifts[ib] = 0;
memset(L, 1, block_size);
continue;
}
@ -4527,7 +4540,12 @@ static void quantize_row_iq1_m_impl(const float * GGML_RESTRICT x, void * GGML_R
}
}
}
GGML_ASSERT(besti1 >= 0 && besti2 >= 0 && best_k >= 0);
if (besti1 < 0 || besti2 < 0 || best_k < 0) {
scales[ib] = 0;
shifts[ib] = 0;
memset(L, 1, block_size);
continue;
}
for (int j = 0; j < besti1; ++j) L[idx[2*j]] = 0;
for (int j = besti1; j < besti2; ++j) L[idx[2*j]] = 1;
for (int j = besti2; j < block_size; ++j) L[idx[2*j]] = 2;
@ -4874,6 +4892,7 @@ static void quantize_row_iq2_s_impl(const float * GGML_RESTRICT x, void * GGML_R
}
float max = xval[0];
for (int i = 1; i < 16; ++i) max = MAX(max, xval[i]);
memset(L, 0, 16);
if (max < GROUP_MAX_EPS_IQ2_S) {
scales[ib] = 0;
continue;

87
tests/test-chat.cpp
View File

@ -637,6 +637,41 @@ static common_chat_tool quoted_unquoted_tool{
};
static common_chat_tool tool_2req_4opt{
/* .name = */ "tool_2req_4opt",
/* .description = */ "Tool with 2 required and 4 optional params",
/* .parameters = */ R"({
"type": "object",
"properties": {
"req1": { "type": "string", "description": "Required string" },
"req2": { "type": "integer", "description": "Required int" },
"opt1": { "type": "string", "description": "Optional string 1" },
"opt2": { "type": "integer", "description": "Optional int 1" },
"opt3": { "type": "string", "description": "Optional string 2" },
"opt4": { "type": "integer", "description": "Optional int 2" }
},
"required": ["req1", "req2"]
})",
};
static common_chat_tool tool_2req_5opt{
/* .name = */ "tool_2req_5opt",
/* .description = */ "Tool with 2 required and 5 optional params",
/* .parameters = */ R"({
"type": "object",
"properties": {
"req1": { "type": "string", "description": "Required string" },
"req2": { "type": "integer", "description": "Required int" },
"opt1": { "type": "string", "description": "Optional string 1" },
"opt2": { "type": "integer", "description": "Optional int 1" },
"opt3": { "type": "string", "description": "Optional string 2" },
"opt4": { "type": "integer", "description": "Optional int 2" },
"opt5": { "type": "string", "description": "Optional string 3" }
},
"required": ["req1", "req2"]
})",
};
static std::vector<common_chat_tool> tools{ special_function_tool, special_function_tool_with_optional_param,
python_tool, html_tool, todo_list };
@ -1958,6 +1993,58 @@ static void test_template_output_peg_parsers(bool detailed_debug) {
{ "todo_list", "{\"todos\": [{\"item\": \"Check stuff\", \"selected\": false}, {\"item\": \"Prepare stuff\", \"selected\": true}]}", {} },
})
.run();
// Test flexible optional argument ordering (2 required + 4 optional, reversed optional order)
tst.test(
"<tool_call>\n"
"<function=tool_2req_4opt>\n"
"<parameter=req1>\nhello\n</parameter>\n"
"<parameter=req2>\n42\n</parameter>\n"
"<parameter=opt4>\n100\n</parameter>\n"
"<parameter=opt2>\n200\n</parameter>\n"
"</function>\n"
"</tool_call>")
.tools({ tool_2req_4opt })
.expect_tool_calls({
{ "tool_2req_4opt", R"({"req1": "hello", "req2": 42, "opt4": 100, "opt2": 200})", {} },
})
.run();
// Test flexible optional argument ordering (2 required + 5 optional, reversed optional order)
tst.test(
"<tool_call>\n"
"<function=tool_2req_5opt>\n"
"<parameter=req1>\nworld\n</parameter>\n"
"<parameter=req2>\n7\n</parameter>\n"
"<parameter=opt5>\nlast\n</parameter>\n"
"<parameter=opt3>\nmiddle\n</parameter>\n"
"<parameter=opt1>\nfirst\n</parameter>\n"
"</function>\n"
"</tool_call>")
.tools({ tool_2req_5opt })
.expect_tool_calls({
{ "tool_2req_5opt", R"({"req1": "world", "req2": 7, "opt5": "last", "opt3": "middle", "opt1": "first"})", {} },
})
.run();
// Test flexible optional argument ordering (2 required + 5 optional, all 5 in shuffled order)
tst.test(
"<tool_call>\n"
"<function=tool_2req_5opt>\n"
"<parameter=req1>\ntest\n</parameter>\n"
"<parameter=req2>\n99\n</parameter>\n"
"<parameter=opt3>\nc\n</parameter>\n"
"<parameter=opt1>\na\n</parameter>\n"
"<parameter=opt5>\ne\n</parameter>\n"
"<parameter=opt4>\n4\n</parameter>\n"
"<parameter=opt2>\n2\n</parameter>\n"
"</function>\n"
"</tool_call>")
.tools({ tool_2req_5opt })
.expect_tool_calls({
{ "tool_2req_5opt", R"({"req1": "test", "req2": 99, "opt3": "c", "opt1": "a", "opt5": "e", "opt4": 4, "opt2": 2})", {} },
})
.run();
}
{
auto tst = peg_tester("models/templates/deepseek-ai-DeepSeek-V3.1.jinja", detailed_debug);