Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.devops/nix/apps.nix
#	.devops/tools.sh
#	Makefile
#	README.md
#	docs/backend/SYCL.md
#	docs/build.md
#	examples/CMakeLists.txt
#	ggml/include/ggml.h
#	src/llama-vocab.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
#	tests/test-sampling.cpp
This commit is contained in:
Concedo 2024-07-27 23:15:54 +08:00
commit ba5babb876
61 changed files with 1389 additions and 5170 deletions

View file

@ -1325,6 +1325,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
else { invalid_param = true; }
return true;
}
if (arg == "--no-warmup") {
params.warmup = false;
return true;
}
#ifndef LOG_DISABLE_LOGS
// Parse args for logging parameters
if (log_param_single_parse(argv[i])) {
@ -1447,6 +1451,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
options.push_back({ "main infill", " --in-prefix-bos", "prefix BOS to user inputs, preceding the `--in-prefix` string" });
options.push_back({ "main infill", " --in-prefix STRING", "string to prefix user inputs with (default: empty)" });
options.push_back({ "main infill", " --in-suffix STRING", "string to suffix after user inputs with (default: empty)" });
options.push_back({ "main", " --no-warmup", "skip warming up the model with an empty run" });
options.push_back({ "server infill",
" --spm-infill", "use Suffix/Prefix/Middle pattern for infill (instead of Prefix/Suffix/Middle) as some models prefer this. (default: %s)", params.spm_infill ? "enabled" : "disabled" });