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

* 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

View file

@ -56,6 +56,7 @@ class ServerProcess:
# custom options
model_alias: str | None = None
model_tags: str | None = None
model_url: str | None = None
model_file: str | None = None
model_draft: str | None = None
@ -180,6 +181,8 @@ class ServerProcess:
server_args.extend(["--pooling", self.pooling])
if self.model_alias:
server_args.extend(["--alias", self.model_alias])
if self.model_tags:
server_args.extend(["--tags", self.model_tags])
if self.n_ctx:
server_args.extend(["--ctx-size", self.n_ctx])
if self.n_slots: