Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '56d2fed2b3970ae55eebd0e5426d402304b1358a' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build.yml
#	.gitignore
#	README.md
#	examples/CMakeLists.txt
#	examples/debug/CMakeLists.txt
#	examples/model-conversion/scripts/causal/compare-logits.py
#	examples/model-conversion/scripts/causal/run-casual-gen-embeddings-org.py
#	examples/model-conversion/scripts/causal/run-converted-model-embeddings-logits.sh
#	examples/model-conversion/scripts/causal/run-converted-model.sh
#	examples/model-conversion/scripts/causal/run-org-model.py
#	examples/model-conversion/scripts/embedding/run-converted-model.sh
#	examples/model-conversion/scripts/embedding/run-original-model.py
#	examples/model-conversion/scripts/utils/common.py
#	examples/model-conversion/scripts/utils/semantic_check.py
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-msg.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-utils.c
#	ggml/src/ggml-hexagon/htp/hvx-utils.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/softmax-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	scripts/snapdragon/adb/run-bench.sh
#	tests/test-arg-parser.cpp
#	tools/CMakeLists.txt
This commit is contained in:
Concedo
2026-01-09 00:30:53 +08:00
parent 4bf6d9eb9a 56d2fed2b3
commit 956ab99934
18 changed files with 1186 additions and 575 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+92 -45
View File
@@ -681,7 +681,6 @@ static void common_params_print_completion(common_params_context & ctx_arg) {
"llama-quantize",
"llama-qwen2vl-cli",
"llama-retrieval",
"llama-run",
"llama-save-load-state",
"llama-server",
"llama-simple",
@@ -856,6 +855,54 @@ bool common_arg_utils::is_autoy(const std::string & value) {
return value == "auto" || value == "-1";
}
// Simple CSV parser that handles quoted fields and escaped quotes
// example:
// input: value1,"value, with, commas","value with ""escaped"" quotes",value4
// output: [value1] [value, with, commas] [value with "escaped" quotes] [value4]
static std::vector<std::string> parse_csv_row(const std::string& input) {
std::vector<std::string> fields;
std::string field;
bool in_quotes = false;
for (size_t i = 0; i < input.length(); ++i) {
char ch = input[i];
if (ch == '"') {
if (!in_quotes) {
// start of quoted field (only valid if at beginning of field)
if (!field.empty()) {
// quote appeared in middle of unquoted field, treat as literal
field += '"';
} else {
in_quotes = true; // start
}
} else {
if (i + 1 < input.length() && input[i + 1] == '"') {
// escaped quote: ""
field += '"';
++i; // skip the next quote
} else {
in_quotes = false; // end
}
}
} else if (ch == ',') {
if (in_quotes) {
field += ',';
} else {
fields.push_back(std::move(field));
field.clear();
}
} else {
field += ch;
}
}
// Add the last field
fields.push_back(std::move(field));
return fields;
}
common_params_context common_params_parser_init(common_params & params, llama_example ex, void(*print_usage)(int, char **)) {
// per-example default params
// we define here to make sure it's included in llama-gen-docs
@@ -1252,7 +1299,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
{"--in-file"}, "FNAME",
"an input file (use comma-separated values to specify multiple files)",
[](common_params & params, const std::string & value) {
for (const auto & item : string_split<std::string>(value, ',')) {
for (const auto & item : parse_csv_row(value)) {
std::ifstream file(item);
if (!file) {
throw std::runtime_error(string_format("error: failed to open file '%s'\n", item.c_str()));
@@ -1399,7 +1446,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params, bool value) {
params.warmup = value;
}
).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_MTMD, LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_RETRIEVAL, LLAMA_EXAMPLE_PERPLEXITY}));
).set_examples({LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_MTMD, LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_RETRIEVAL, LLAMA_EXAMPLE_PERPLEXITY, LLAMA_EXAMPLE_DEBUG}));
add_opt(common_arg(
{"--spm-infill"},
string_format(
@@ -1715,7 +1762,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
else if (value == "rank") { params.pooling_type = LLAMA_POOLING_TYPE_RANK; }
else { throw std::invalid_argument("invalid value"); }
}
).set_examples({LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_RETRIEVAL, LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_POOLING"));
).set_examples({LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_RETRIEVAL, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_DEBUG}).set_env("LLAMA_ARG_POOLING"));
add_opt(common_arg(
{"--attention"}, "{causal,non-causal}",
"attention type for embeddings, use model default if unspecified",
@@ -2004,7 +2051,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
{"--image", "--audio"}, "FILE",
"path to an image or audio file. use with multimodal models, use comma-separated values for multiple files\n",
[](common_params & params, const std::string & value) {
for (const auto & item : string_split<std::string>(value, ',')) {
for (const auto & item : parse_csv_row(value)) {
params.image.emplace_back(item);
}
}
@@ -2261,37 +2308,12 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
));
add_opt(common_arg(
{"--override-kv"}, "KEY=TYPE:VALUE,...",
"advanced option to override model metadata by key. to specify multiple overrides, either use comma-separated or repeat this argument.\n"
"advanced option to override model metadata by key. to specify multiple overrides, either use comma-separated values.\n"
"types: int, float, bool, str. example: --override-kv tokenizer.ggml.add_bos_token=bool:false,tokenizer.ggml.add_eos_token=bool:false",
[](common_params & params, const std::string & value) {
std::vector<std::string> kv_overrides;
std::string current;
bool escaping = false;
for (const char c : value) {
if (escaping) {
current.push_back(c);
escaping = false;
} else if (c == '\\') {
escaping = true;
} else if (c == ',') {
kv_overrides.push_back(current);
current.clear();
} else {
current.push_back(c);
}
}
if (escaping) {
current.push_back('\\');
}
kv_overrides.push_back(current);
for (const auto & kv_override : kv_overrides) {
if (!string_parse_kv_override(kv_override.c_str(), params.kv_overrides)) {
throw std::runtime_error(string_format("error: Invalid type for KV override: %s\n", kv_override.c_str()));
for (const auto & item : parse_csv_row(value)) {
if (!string_parse_kv_override(item.c_str(), params.kv_overrides)) {
throw std::runtime_error(string_format("error: Invalid type for KV override: %s\n", item.c_str()));
}
}
}
@@ -2308,7 +2330,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
{"--lora"}, "FNAME",
"path to LoRA adapter (use comma-separated values to load multiple adapters)",
[](common_params & params, const std::string & value) {
for (const auto & item : string_split<std::string>(value, ',')) {
for (const auto & item : parse_csv_row(value)) {
params.lora_adapters.push_back({ item, 1.0, "", "", nullptr });
}
}
@@ -2319,7 +2341,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
"path to LoRA adapter with user defined scaling (format: FNAME:SCALE,...)\n"
"note: use comma-separated values",
[](common_params & params, const std::string & value) {
for (const auto & item : string_split<std::string>(value, ',')) {
for (const auto & item : parse_csv_row(value)) {
auto parts = string_split<std::string>(item, ':');
if (parts.size() != 2) {
throw std::invalid_argument("lora-scaled format: FNAME:SCALE");
@@ -2333,7 +2355,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
{"--control-vector"}, "FNAME",
"add a control vector\nnote: use comma-separated values to add multiple control vectors",
[](common_params & params, const std::string & value) {
for (const auto & item : string_split<std::string>(value, ',')) {
for (const auto & item : parse_csv_row(value)) {
params.control_vectors.push_back({ 1.0f, item, });
}
}
@@ -2343,7 +2365,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
"add a control vector with user defined scaling SCALE\n"
"note: use comma-separated values (format: FNAME:SCALE,...)",
[](common_params & params, const std::string & value) {
for (const auto & item : string_split<std::string>(value, ',')) {
for (const auto & item : parse_csv_row(value)) {
auto parts = string_split<std::string>(item, ':');
if (parts.size() != 2) {
throw std::invalid_argument("control-vector-scaled format: FNAME:SCALE");
@@ -2441,7 +2463,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
{"--context-file"}, "FNAME",
"file to load context from (use comma-separated values to specify multiple files)",
[](common_params & params, const std::string & value) {
for (const auto & item : string_split<std::string>(value, ',')) {
for (const auto & item : parse_csv_row(value)) {
std::ifstream file(item, std::ios::binary);
if (!file) {
throw std::runtime_error(string_format("error: failed to open file '%s'\n", item.c_str()));
@@ -2588,7 +2610,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params, int value) {
params.embd_normalize = value;
}
).set_examples({LLAMA_EXAMPLE_EMBEDDING}));
).set_examples({LLAMA_EXAMPLE_EMBEDDING, LLAMA_EXAMPLE_DEBUG}));
add_opt(common_arg(
{"--embd-output-format"}, "FORMAT",
"empty = default, \"array\" = [[],[]...], \"json\" = openai style, \"json+\" = same \"json\" + cosine similarity matrix, \"raw\" = plain whitespace-delimited output (one embedding per line)",
@@ -2666,7 +2688,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params) {
params.embedding = true;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_EMBEDDINGS"));
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_DEBUG}).set_env("LLAMA_ARG_EMBEDDINGS"));
add_opt(common_arg(
{"--rerank", "--reranking"},
string_format("enable reranking endpoint on server (default: %s)", "disabled"),
@@ -2677,9 +2699,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_RERANKING"));
add_opt(common_arg(
{"--api-key"}, "KEY",
"API key to use for authentication (default: none)",
"API key to use for authentication, multiple keys can be provided as a comma-separated list (default: none)",
[](common_params & params, const std::string & value) {
params.api_keys.push_back(value);
for (const auto & key : parse_csv_row(value)) {
if (!key.empty()) {
params.api_keys.push_back(key);
}
}
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_API_KEY"));
add_opt(common_arg(
@@ -2693,7 +2719,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
std::string key;
while (std::getline(key_file, key)) {
if (!key.empty()) {
params.api_keys.push_back(key);
params.api_keys.push_back(key);
}
}
key_file.close();
@@ -2715,7 +2741,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_SSL_CERT_FILE"));
add_opt(common_arg(
{"--chat-template-kwargs"}, "STRING",
string_format("sets additional params for the json template parser"),
"sets additional params for the json template parser, must be a valid json object string, e.g. '{\"key1\":\"value1\",\"key2\":\"value2\"}'",
[](common_params & params, const std::string & value) {
auto parsed = json::parse(value);
for (const auto & item : parsed.items()) {
@@ -3353,6 +3379,27 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
}
).set_examples({ LLAMA_EXAMPLE_FINETUNE }));
add_opt(common_arg(
{"--save-logits"},
string_format("save final logits to files for verification (default: %s)", params.save_logits ? "true" : "false"),
[](common_params & params) {
params.save_logits = true;
}
).set_examples({LLAMA_EXAMPLE_DEBUG}));
add_opt(common_arg(
{"--logits-output-dir"}, "PATH",
string_format("directory for saving logits output files (default: %s)", params.logits_output_dir.c_str()),
[](common_params & params, const std::string & value) {
params.logits_output_dir = value;
}
).set_examples({LLAMA_EXAMPLE_DEBUG}));
add_opt(common_arg(
{"--tensor-filter"}, "REGEX",
"filter tensor names for debug output (regex pattern, can be specified multiple times)",
[](common_params & params, const std::string & value) {
params.tensor_filter.push_back(value);
}
).set_examples({LLAMA_EXAMPLE_DEBUG}));
// presets
add_opt(common_arg(