wylab/llama.cpp
0
0
Fork 1
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-14 18:02:52 +02:00
Code Issues Packages Projects Releases Wiki Activity

revert some excessive changes

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-08-21 22:56:42 +02:00
parent 03eb25f393
commit 173d7e804e
12 changed files with 27 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/chat.cpp
+1 -1
View File
@@ -968,7 +968,7 @@ static std::string common_chat_template_direct_apply_impl(
jinja::caps_apply_preserve_reasoning(ctx, enabled);
}
if (inp.contains("reasoning_effort") && inp["reasoning_effort"].is_string() && !inp["reasoning_effort"].empty()) {
std::string reasoning_effort = inp["reasoning_effort"];
std::string reasoning_effort = inp["reasoning_effort"].get<std::string>();
jinja::caps_apply_reasoning_effort(ctx, reasoning_effort);
}
common/download.cpp
+1 -1
View File
@@ -921,7 +921,7 @@ std::string common_docker_resolve_model(const std::string & docker) {
if (manifest.contains("layers")) {
for (const auto & layer : manifest["layers"]) {
if (layer.contains("mediaType")) {
std::string media_type = layer["mediaType"];
std::string media_type = layer["mediaType"].get<std::string>();
if (media_type == "application/vnd.docker.ai.gguf.v3" ||
media_type.find("gguf") != std::string::npos) {
gguf_digest = layer["digest"].get<std::string>();
common/hf-cache.cpp
+2 -2
View File
@@ -244,8 +244,8 @@ static std::string get_repo_commit(const std::string & repo_id,
!branch.contains("targetCommit") || !branch["targetCommit"].is_string()) {
continue;
}
std::string _name = branch["name"];
std::string _commit = branch["targetCommit"];
std::string _name = branch["name"].get<std::string>();
std::string _commit = branch["targetCommit"].get<std::string>();
if (!is_valid_subpath(refs_path, _name)) {
LOG_WRN("%s: skip invalid branch: %s\n", __func__, _name.c_str());
tests/gguf-model-data.cpp
+1 -1
View File
@@ -475,7 +475,7 @@ static std::string detect_gguf_filename(const std::string & repo, const std::str
for (const auto & sibling : j["siblings"]) {
if (!sibling.contains("rfilename")) { continue; }
std::string fname = sibling["rfilename"];
std::string fname = sibling["rfilename"].get<std::string>();
if (fname.size() < 5 || fname.substr(fname.size() - 5) != ".gguf") {
continue;
}
tests/test-chat.cpp
+1 -1
View File
@@ -7052,7 +7052,7 @@ static void test_reasoning_budget_message_per_request() {
if (!llama_params.contains("reasoning_budget_message")) {
throw std::runtime_error("reasoning_budget_message missing from llama_params (thinking_end_tag may be empty for this template)");
}
std::string got = llama_params["reasoning_budget_message"];
std::string got = llama_params["reasoning_budget_message"].get<std::string>();
if (got != per_request_message) {
throw std::runtime_error("Expected reasoning_budget_message='" + per_request_message + "', got '" + got + "'");
}
tools/cli/cli-context.cpp
+3 -3
View File
@@ -218,7 +218,7 @@ bool cli_context::list_and_ask_models() {
if (!m.contains("id") || !m.at("id").is_string()) {
continue;
}
std::string name = m.at("id");
std::string name = m.at("id").get<std::string>();
std::string display = name;
if (m.contains("aliases") && m.at("aliases").is_array()) {
std::vector<std::string> aliases;
@@ -387,14 +387,14 @@ bool cli_context::generate_completion(generated_content & content_out, cli_timin
}
const auto & delta = choice.at("delta");
if (delta.contains("reasoning_content") && delta.at("reasoning_content").is_string()) {
const std::string text = delta.at("reasoning_content");
const std::string text = delta.at("reasoning_content").get<std::string>();
if (!text.empty()) {
content_out.reasoning += text;
a.push(ui::ASSISTANT_DISPLAY_MODE_REASONING, text);
}
}
if (delta.contains("content") && delta.at("content").is_string()) {
const std::string text = delta.at("content");
const std::string text = delta.at("content").get<std::string>();
if (!text.empty()) {
content_out.content += text;
a.push(ui::ASSISTANT_DISPLAY_MODE_CONTENT, text);
tools/server/server-chat.cpp
+2 -2
View File
@@ -679,12 +679,12 @@ json convert_transcriptions_to_chatcmpl(
chatcmpl_body["stream"] = stream == "true";
if (inp_body.contains("max_tokens")) {
std::string inp = inp_body["max_tokens"];
std::string inp = inp_body["max_tokens"].get<std::string>();
chatcmpl_body["max_tokens"] = std::stoul(inp);
}
if (inp_body.contains("temperature")) {
std::string inp = inp_body["temperature"];
std::string inp = inp_body["temperature"].get<std::string>();
chatcmpl_body["temperature"] = std::stof(inp);
}
tools/server/server-context.cpp
+2 -2
View File
@@ -5103,7 +5103,7 @@ void server_routes::init_routes() {
std::vector<server_task> tasks;
tasks.reserve(documents.size());
for (size_t i = 0; i < documents.size(); i++) {
auto tmp = format_prompt_rerank(ctx_server.model_tgt, ctx_server.vocab, ctx_server.mctx, query.get<std::string>(), documents[i]);
auto tmp = format_prompt_rerank(ctx_server.model_tgt, ctx_server.vocab, ctx_server.mctx, query, documents[i]);
server_task task = server_task(SERVER_TASK_TYPE_RERANK);
task.id = rd.get_new_id();
task.tokens = std::move(tmp);
@@ -5332,7 +5332,7 @@ std::unique_ptr<server_res_generator> server_routes::handle_embeddings_impl(cons
bool use_base64 = false;
if (body.count("encoding_format") != 0) {
const std::string format = body.at("encoding_format");
const std::string & format = body.at("encoding_format");
if (format == "base64") {
use_base64 = true;
} else if (format != "float") {
tools/server/server-http.cpp
+1 -1
View File
@@ -785,7 +785,7 @@ void server_http_context::register_gcp_compat() const {
try {
json payload = instance;
const std::string format = payload.at("@requestFormat");
const std::string format = payload.at("@requestFormat").get<std::string>();
payload.erase("@requestFormat");
if (payload.contains("stream")) {
tools/server/server-schema.cpp
+3 -3
View File
@@ -306,7 +306,7 @@ std::vector<std::unique_ptr<field>> make_llama_cmpl_schema(const common_params &
add((new field_str("generation_prompt"))
->set_desc("Generation prompt appended to the chat template output")
->set_handler([&](field_eval_context & ctx, const json & data) {
std::string s = data.at("generation_prompt");
std::string s = data.at("generation_prompt").get<std::string>();
ctx.params.chat_parser_params.generation_prompt = s;
ctx.params.sampling.generation_prompt = s;
}));
@@ -399,13 +399,13 @@ std::vector<std::unique_ptr<field>> make_llama_cmpl_schema(const common_params &
ctx.params.sampling.reasoning_budget_end.clear();
if (data.contains("reasoning_budget_end_tags")) {
for (const auto & t : data.at("reasoning_budget_end_tags")) {
std::string tag = t;
std::string tag = t.get<std::string>();
if (!tag.empty()) {
ctx.params.sampling.reasoning_budget_end.push_back(common_tokenize(ctx.vocab, tag, false, true));
}
}
} else if (data.contains("reasoning_budget_end_tag")) {
std::string tag = data.at("reasoning_budget_end_tag");
std::string tag = data.at("reasoning_budget_end_tag").get<std::string>();
if (!tag.empty()) {
ctx.params.sampling.reasoning_budget_end.push_back(common_tokenize(ctx.vocab, tag, false, true));
}
tools/server/server-stream.cpp
+1 -1
View File
@@ -510,7 +510,7 @@ server_http_context::handler_t server_stream_make_lookup_handler() {
if (body.contains("conversation_ids") && body["conversation_ids"].is_array()) {
for (const auto & v : body["conversation_ids"]) {
if (v.is_string()) {
std::string id = v;
std::string id = v.get<std::string>();
if (!id.empty()) {
requested.push_back(std::move(id));
}
tools/server/server-tools.cpp
+9 -9
View File
@@ -896,7 +896,7 @@ struct server_tool_read_file : server_tool {
}
json invoke(json params, server_tool::stream *) const override {
std::string path = params.at("path");
std::string path = params.at("path").get<std::string>();
int start_line = json_value(params, "start_line", 1);
int end_line = json_value(params, "end_line", -1); // -1 = no limit
bool append_loc = json_value(params, "append_loc", false);
@@ -1015,7 +1015,7 @@ struct server_tool_file_glob_search : server_tool {
json invoke(json params, server_tool::stream *) const override {
auto io = make_tools_io(params);
const std::string path = params.at("path");
const std::string path = params.at("path").get<std::string>();
std::string base = io->resolve(path);
std::string include = json_value(params, "include", std::string("**"));
@@ -1128,8 +1128,8 @@ struct server_tool_grep_search : server_tool {
}
json invoke(json params, server_tool::stream *) const override {
std::string path = params.at("path");
std::string pat_str = params.at("pattern");
std::string path = params.at("path").get<std::string>();
std::string pat_str = params.at("pattern").get<std::string>();
std::string include = json_value(params, "include", std::string("**"));
std::string exclude = json_value(params, "exclude", std::string(""));
bool show_lineno = json_value(params, "return_line_numbers", false);
@@ -1271,7 +1271,7 @@ struct server_tool_exec_shell_command : server_tool {
}
json invoke(json params, server_tool::stream * st) const override {
std::string command = params.at("command");
std::string command = params.at("command").get<std::string>();
int timeout = json_value(params, "timeout", 10);
size_t max_output = (size_t) json_value(params, "max_output_size", (int) SERVER_TOOL_EXEC_SHELL_COMMAND_MAX_OUTPUT_SIZE);
@@ -1348,8 +1348,8 @@ struct server_tool_write_file : server_tool {
}
json invoke(json params, server_tool::stream *) const override {
std::string path = params.at("path");
std::string content = params.at("content");
std::string path = params.at("path").get<std::string>();
std::string content = params.at("content").get<std::string>();
auto io = make_tools_io(params);
if (!io->write_file(path, content)) {
@@ -1405,7 +1405,7 @@ struct server_tool_edit_file : server_tool {
}
json invoke(json params, server_tool::stream *) const override {
std::string path = params.at("path");
std::string path = params.at("path").get<std::string>();
const json & edits_json = params.at("edits");
if (!edits_json.is_array() || edits_json.empty()) {
@@ -2078,7 +2078,7 @@ void server_tools::setup(const std::vector<std::string> & enabled_tools,
auto res = std::make_unique<server_tools_res>();
try {
json body = json::parse(req.body);
std::string tool_name = body.at("tool");
std::string tool_name = body.at("tool").get<std::string>();
json params = body.value("params", json::object());
bool stream = body.value("stream", false);