Daniel HiltgenandGitHub 9d35332880 server: reuse verified manifests and loaded models in inference routes (#18947) ...

* server: reuse verified manifests and loaded models in inference routes

Resolve named manifests and runner selection in one verified cold lookup.
When a runner is loaded, reuse its model after checking that the v2 tag
still points to the same digest. Fully verify regular-file manifests,
including Windows copies.

Share the lookup across generate, chat, embed, and System One. Keep parser
selection request-local so reusing a model does not mutate its config.

Cover tag changes, runner selection, concurrent unloads, and existing
missing-model responses with regression tests and a lookup benchmark.

* address comments

2026-10-12 08:41:52 -07:00

..

downgrade_test.go

llama-server: prepare to remove compatibility patch

2026-09-24 19:25:52 -07:00

layer.go

llama-server: prepare to remove compatibility patch

2026-09-24 19:25:52 -07:00

manifest_test.go

server: reuse verified manifests and loaded models in inference routes (#18947)

2026-10-12 08:41:52 -07:00

manifest.go

server: reuse verified manifests and loaded models in inference routes (#18947)

2026-10-12 08:41:52 -07:00

paths.go

manifest: avoid symlinks on Windows (#18852)

2026-10-07 12:53:35 -07:00