vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
#	tests/test-grad0.cpp
This commit is contained in:
Concedo 2024-09-21 11:23:54 +08:00
commit cd1a52a29e
28 changed files with 809 additions and 120 deletions
Download patch file Download diff file Expand all files Collapse all files

30
examples/quantize/quantize.cpp
View file

@ -64,6 +64,16 @@ static const char * const LLM_KV_QUANTIZE_IMATRIX_DATASET = "quantize.imatrix
static const char * const LLM_KV_QUANTIZE_IMATRIX_N_ENTRIES = "quantize.imatrix.entries_count";
static const char * const LLM_KV_QUANTIZE_IMATRIX_N_CHUNKS = "quantize.imatrix.chunks_count";
static bool striequals(const char * a, const char * b) {
while (*a && *b) {
if (std::tolower(*a) != std::tolower(*b)) {
return false;
}
a++; b++;
}
return *a == *b;
}
static bool try_parse_ftype(const std::string & ftype_str_in, llama_ftype & ftype, std::string & ftype_str_out) {
std::string ftype_str;
@ -71,7 +81,7 @@ static bool try_parse_ftype(const std::string & ftype_str_in, llama_ftype & ftyp
ftype_str.push_back(std::toupper(ch));
}
for (auto & it : QUANT_OPTIONS) {
if (it.name == ftype_str) {
if (striequals(it.name.c_str(), ftype_str.c_str())) {
ftype = it.ftype;
ftype_str_out = it.name;
return true;
@ -226,15 +236,15 @@ static int prepare_imatrix(const std::string & imatrix_file,
}
static ggml_type parse_ggml_type(const char * arg) {
ggml_type result = GGML_TYPE_COUNT;
for (int j = 0; j < GGML_TYPE_COUNT; ++j) {
auto type = ggml_type(j);
for (int i = 0; i < GGML_TYPE_COUNT; ++i) {
auto type = (ggml_type)i;
const auto * name = ggml_type_name(type);
if (name && strcmp(arg, name) == 0) {
result = type; break;
if (name && striequals(name, arg)) {
return type;
}
}
return result;
fprintf(stderr, "%s: invalid ggml_type '%s'\n", __func__, arg);
return GGML_TYPE_COUNT;
}
int main(int argc, char ** argv) {
@ -255,12 +265,18 @@ int main(int argc, char ** argv) {
} else if (strcmp(argv[arg_idx], "--output-tensor-type") == 0) {
if (arg_idx < argc-1) {
params.output_tensor_type = parse_ggml_type(argv[++arg_idx]);
if (params.output_tensor_type == GGML_TYPE_COUNT) {
usage(argv[0]);
}
} else {
usage(argv[0]);
}
} else if (strcmp(argv[arg_idx], "--token-embedding-type") == 0) {
if (arg_idx < argc-1) {
params.token_embedding_type = parse_ggml_type(argv[++arg_idx]);
if (params.token_embedding_type == GGML_TYPE_COUNT) {
usage(argv[0]);
}
} else {
usage(argv[0]);
}