thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

server : support multiple model aliases via comma-separated --alias (#19926)

Browse source 
* server : support multiple model aliases via comma-separated --alias

* server : update --alias description and regenerate docs

* server : multiple model aliases and tags

- address review feedback from ngxson
- --alias accepts comma-separated values (std::set, no duplicates)
- --tags for informational metadata (not used for routing)
- aliases resolve transparently in router via get_meta/has_model
- /v1/models exposes aliases and tags fields

* regenerate docs

* nits

* server : use first alias as model_name for backward compat

address review feedback from ngxson

* server : add single-model test for aliases and tags
This commit is contained in:
Pascal 2026-02-27 07:05:23 +01:00 • committed by GitHub
parent a8b192b6ec
commit 2e7e638523
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 173 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

21
common/arg.cpp
View file

@ -2520,11 +2520,28 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
));
add_opt(common_arg(
{"-a", "--alias"}, "STRING",
"set alias for model name (to be used by REST API)",
"set model name aliases, comma-separated (to be used by API)",
[](common_params & params, const std::string & value) {
params.model_alias = value;
for (auto & alias : string_split<std::string>(value, ',')) {
alias = string_strip(alias);
if (!alias.empty()) {
params.model_alias.insert(alias);
}
}
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_ALIAS"));
add_opt(common_arg(
{"--tags"}, "STRING",
"set model tags, comma-separated (informational, not used for routing)",
[](common_params & params, const std::string & value) {
for (auto & tag : string_split<std::string>(value, ',')) {
tag = string_strip(tag);
if (!tag.empty()) {
params.model_tags.insert(tag);
}
}
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_TAGS"));
add_opt(common_arg(
{"-m", "--model"}, "FNAME",
ex == LLAMA_EXAMPLE_EXPORT_LORA