vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

common: llama_load_model_from_url split support (#6192)

Browse source 
* llama: llama_split_prefix fix strncpy does not include string termination
common: llama_load_model_from_url:
 - fix header name case sensitive
 - support downloading additional split in parallel
 - hide password in url

* common: EOL EOF

* common: remove redundant LLAMA_CURL_MAX_PATH_LENGTH definition

* common: change max url max length

* common: minor comment

* server: support HF URL options

* llama: llama_model_loader fix log

* common: use a constant for max url length

* common: clean up curl if file cannot be loaded in gguf

* server: tests: add split tests, and HF options params

* common: move llama_download_hide_password_in_url inside llama_download_file as a lambda

* server: tests: enable back Release test on PR

* spacing

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* spacing

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* spacing

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Pierrick Hymbert 2024-03-23 18:07:00 +01:00 • committed by GitHub
parent 1997577d5e
commit f482bb2e49
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 200 additions and 63 deletions
Download patch file Download diff file Expand all files Collapse all files

18
examples/server/server.cpp
View file

@ -2208,7 +2208,11 @@ static void server_print_usage(const char * argv0, const gpt_params & params, co
printf(" -m FNAME, --model FNAME\n");
printf(" model path (default: %s)\n", params.model.c_str());
printf(" -mu MODEL_URL, --model-url MODEL_URL\n");
printf(" model download url (default: %s)\n", params.model_url.c_str());
printf(" model download url (default: unused)\n");
printf(" -hfr REPO, --hf-repo REPO\n");
printf(" Hugging Face model repository (default: unused)\n");
printf(" -hff FILE, --hf-file FILE\n");
printf(" Hugging Face model file (default: unused)\n");
printf(" -a ALIAS, --alias ALIAS\n");
printf(" set an alias for the model, will be added as `model` field in completion response\n");
printf(" --lora FNAME apply LoRA adapter (implies --no-mmap)\n");
@ -2337,6 +2341,18 @@ static void server_params_parse(int argc, char ** argv, server_params & sparams,
break;
}
params.model_url = argv[i];
} else if (arg == "-hfr" || arg == "--hf-repo") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.hf_repo = argv[i];
} else if (arg == "-hff" || arg == "--hf-file") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.hf_file = argv[i];
} else if (arg == "-a" || arg == "--alias") {
if (++i >= argc) {
invalid_param = true;